WO2024051267A1 - Capacity management method and related system - Google Patents

Capacity management method and related system Download PDF

Info

Publication number
WO2024051267A1
WO2024051267A1 PCT/CN2023/101337 CN2023101337W WO2024051267A1 WO 2024051267 A1 WO2024051267 A1 WO 2024051267A1 CN 2023101337 W CN2023101337 W CN 2023101337W WO 2024051267 A1 WO2024051267 A1 WO 2024051267A1
Authority
WO
WIPO (PCT)
Prior art keywords
resource pool
dimension
dedicated
virtual machines
capacity
Prior art date
Application number
PCT/CN2023/101337
Other languages
French (fr)
Chinese (zh)
Inventor
周文礼
杜天琳
朱磊
苏利
Original Assignee
华为云计算技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为云计算技术有限公司 filed Critical 华为云计算技术有限公司
Publication of WO2024051267A1 publication Critical patent/WO2024051267A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]

Definitions

  • This application relates to the field of cloud computing technology, and in particular, to a capacity management method, system, computing device cluster, computer-readable storage medium, and computer program product.
  • Dedicated Host is a service model in cloud services where users can directly purchase the entire host instead of a virtual machine.
  • Dedicated hosts have the characteristics of exclusive physical resources and more flexible deployment. They do not share capacity with other users and can control the deployment method of virtual machines (VMs) on dedicated hosts.
  • VMs virtual machines
  • Dedicated resource pool services have become the first choice for high-end users when deploying services due to their high resource isolation and users' absolute control.
  • exclusive resource pool service users have absolute control over their own exclusive resource pool. For example, users can freely manage the resource distribution on a dedicated host cluster, and can even specify which host the VM is deployed on, as well as the specific parameters of each hard disk and network.
  • This application provides a capacity management method that collects resource usage in a dedicated resource pool and presents capacity scaling suggestions to the user when it is determined that the dedicated resource pool meets the capacity scaling conditions based on the resource usage, thereby achieving the goal of solving the problem caused by insufficient resources.
  • the issuable amount is reduced, users are reminded to purchase more exclusive resources as soon as possible to expand the capacity, or when resource usage is at a low level for a long time, users are reminded that there may be excess capacity and can appropriately unsubscribe from some exclusive resources to reduce capacity, thus solving the problem of exclusive resource pools.
  • This application also provides systems, computing device clusters, computer-readable storage media and computer program products corresponding to the above methods.
  • this application provides a capacity management method.
  • This method can be executed by the capacity management system on the cloud platform side.
  • the cloud platform provides exclusive resource pool services to users, and the container management system is used to perform capacity management on the exclusive resource pool belonging to the user when the user uses the exclusive resource pool service.
  • the capacity management system can be a software system, which can be integrated into the cloud platform or used independently.
  • the capacity management system can be deployed in a computing device cluster, such as a cluster in a cloud computing data center.
  • the computing device cluster executes the program code of the software system, thereby executing the capacity management method.
  • the capacity management system may also be a hardware system, such as a cluster of computing devices with capacity management functions. When the hardware system is running, the capacity management method of this application is executed.
  • the capacity management system obtains the resource usage of at least one dimension in the exclusive resource pool, determines the measurement value corresponding to the monitoring indicator item of the exclusive resource pool based on the resource usage of at least one dimension, and determines the measurement value corresponding to the monitoring indicator item of the exclusive resource pool.
  • the alarm threshold corresponding to the indicator item determines whether the dedicated resource pool meets the capacity scaling conditions. When the dedicated resource pool meets the capacity scaling conditions, capacity scaling suggestions are presented to the user.
  • This method collects the resource usage in the dedicated resource pool and presents capacity scaling suggestions to the user when it is determined that the dedicated resource pool meets the capacity scaling conditions based on the resource usage, thereby reminding the user to purchase replacements as soon as possible when insufficient resources lead to a reduction in the amount that can be issued.
  • the monitoring indicator items include one or more of the number of virtual machines that can be allocated by the remaining resources of the dedicated resource pool or the resource usage rate.
  • the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool can also be called the number that can be issued.
  • the capacity management system can promptly remind users to expand capacity by monitoring the amount that can be issued, and by monitoring resource usage, it can promptly remind users to shrink capacity and reduce costs.
  • the monitoring indicator item includes the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool.
  • the capacity management system can be based on the total amount of resources in at least one dimension of the dedicated resource pool and at least Based on the resource usage in one dimension, determine the amount of remaining resources in at least one dimension in the dedicated resource pool, and then determine the amount of resources in the dedicated resource pool based on the amount of remaining resources in at least one dimension in the dedicated resource pool and the resource demand of the virtual machine in at least one dimension. The number of virtual machines that can be allocated with remaining resources.
  • This method first determines the amount of remaining resources, and then based on the amount of remaining resources and the resource demand of the virtual machine in at least one dimension, it can more accurately calculate the number of virtual machines that can be issued with the remaining resources. Expansion alarms based on this number have higher Credibility and ability to meet business needs.
  • the capacity management system can also receive a list of virtual machines configured by users through the capacity management interface.
  • the virtual machine list records at least one virtual machine that the user is concerned about. Then the capacity management system can also determine the resource requirement of at least one virtual machine in at least one dimension according to the specifications of at least one virtual machine in the virtual machine list.
  • the virtual machine list records multiple virtual machines that the user is interested in.
  • the capacity management system can also receive the provisioning ratios of multiple virtual machines configured by users through the capacity management interface.
  • the capacity management system may determine the amount of resources remaining in the dedicated resource pool in at least one dimension, the resource requirements of the multiple virtual machines in at least one dimension, and the issuance ratio of the multiple virtual machines. The number of virtual machines that can be allocated from the remaining resources of the dedicated resource pool when the allocation ratio is allocated.
  • the monitoring indicator item includes resource usage.
  • the capacity management system may determine the resource usage rate of the at least one dimension based on the total amount of resources of at least one dimension in the dedicated resource pool and the resource usage of the at least one dimension.
  • This method is based on the total amount of resources in at least one dimension and the resource usage in at least one dimension in the dedicated resource pool, and can accurately determine the resource usage in at least one dimension, which can provide help for scaling down recommendations.
  • the capacity management system can also receive a dedicated resource pool creation request, where the dedicated resource pool creation request includes business parameters input by the user.
  • the capacity management system can determine the type of dedicated host based on the service type in the service parameters and the specifications of the virtual machines used to implement the service, and then determine the number of dedicated hosts of the corresponding type based on the number of virtual machines in the service parameters, and then Recommend the type and quantity of the dedicated hosts to the user.
  • This method supports allowing the user to input business parameters when purchasing exclusive resource pool services, and recommends the user to specifically purchase exclusive resources such as the type and quantity of exclusive hosts based on the business parameters to meet the user's business requirements. This solves the problem of users purchasing an unreasonable number of exclusive resources due to lack of knowledge or experience when purchasing exclusive resource pool services.
  • the number of virtual machines in the business parameters includes the number of virtual machines that need to be added this time. This can at least meet current business needs.
  • the number of virtual machines in the service parameters also includes the total number of virtual machines or the number of virtual machines that need to be added when the load increases. This can meet business needs during the entire life cycle or when the load increases later.
  • resources in at least one dimension include computing resources, storage resources, or network resources. This method performs statistics and calculations on resources in different dimensions, and determines the final calculation results based on the calculation results of each dimension. , which can improve the accuracy of the calculation results.
  • the capacity management system can also record risk events.
  • the risk events can include failure of virtual machine provisioning due to insufficient resources.
  • the capacity management system can also adjust alarm thresholds based on risk events. For example, the capacity management system can increase the alarm threshold corresponding to the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool based on risk events. This can reduce the probability of risk events occurring during subsequent use of the dedicated resource pool.
  • this application provides a capacity management system.
  • the capacity management system is deployed on the cloud platform side, and the cloud platform provides users with exclusive Resource pool service, the container management system is used to perform capacity management on the exclusive resource pool belonging to the user when the user uses the exclusive resource pool service.
  • the capacity management system includes a capacity management device, and the capacity management device includes:
  • An acquisition module used to acquire the resource usage of at least one dimension in the exclusive resource pool
  • a monitoring module configured to determine the measurement value corresponding to the monitoring indicator item of the exclusive resource pool based on the resource usage of the at least one dimension
  • An alarm module configured to determine whether the dedicated resource pool meets the capacity scaling condition based on the measured value of the monitoring indicator item and the alarm threshold corresponding to the monitoring indicator item. When the dedicated resource pool meets the capacity scaling condition, , presenting capacity scaling suggestions to the user.
  • the monitoring indicator items include one or more of the number of virtual machines that can be allocated by the remaining resources of the dedicated resource pool or the resource usage rate.
  • the monitoring indicator item includes the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool;
  • the monitoring module is specifically used for:
  • the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool is determined based on the amount of remaining resources in at least one dimension of the dedicated resource pool and the resource demand of the virtual machines in at least one dimension.
  • the capacity management device further includes:
  • a configuration module configured to receive a virtual machine list configured by the user through the capacity management interface, where the virtual machine list records at least one virtual machine that the user is concerned about;
  • the monitoring module is also used to:
  • the virtual machine list records multiple virtual machines that the user is interested in;
  • the configuration module is also used to:
  • the monitoring module is specifically used for:
  • the resource demand of the multiple virtual machines in at least one dimension, and the issuance ratio of the multiple virtual machines determine the amount of resources when issuing according to the issuance ratio.
  • the monitoring indicator items include resource usage
  • the monitoring module is specifically used for:
  • the resource usage rate of the at least one dimension is determined based on the total amount of resources of at least one dimension in the dedicated resource pool and the resource usage of the at least one dimension.
  • the system further includes a capacity recommendation device, and the capacity recommendation device includes:
  • a communication module configured to receive a dedicated resource pool creation request, where the dedicated resource pool creation request includes business parameters input by the user;
  • a determination module configured to determine the type of the dedicated host based on the service type in the service parameters and the specifications of the virtual machine used to implement the service;
  • the determination module is also used to determine the number of dedicated hosts of the corresponding type according to the number of virtual machines in the business parameters;
  • a recommendation module is used to recommend the type and quantity of the dedicated hosts to the user.
  • the number of virtual machines in the service parameters includes the number of virtual machines that need to be added this time.
  • the number of virtual machines in the service parameters also includes the total number of virtual machines or the number of virtual machines that need to be added when the load increases.
  • this application provides a computing device cluster.
  • the cluster of computing devices includes at least one computing device including at least one processor and at least one memory.
  • the at least one processor and the at least one memory communicate with each other.
  • the at least one processor is configured to execute instructions stored in the at least one memory, so that the computing device or the computing device cluster executes the capacity management method as described in the first aspect or any implementation of the first aspect.
  • the present application provides a computer-readable storage medium in which instructions are stored, and the instructions instruct a computing device or a cluster of computing devices to execute the above-mentioned first aspect or any one of the first aspects. Implement the capacity management method described in the manner.
  • the present application provides a computer program product containing instructions that, when run on a computing device or a cluster of computing devices, cause the computing device or a cluster of computing devices to execute the first aspect or any one of the first aspects. Implement the capacity management method described in the manner.
  • Figure 1 is a schematic architectural diagram of a capacity management system provided by an embodiment of the present application.
  • Figure 2 is a flow chart of a capacity management method provided by an embodiment of the present application.
  • FIG. 3 is a schematic diagram of an exclusive resource pool creation interface provided by an embodiment of the present application.
  • Figure 4 is a schematic diagram of a capacity management interface provided by an embodiment of the present application.
  • Figure 5 is a schematic structural diagram of a capacity management system provided by an embodiment of the present application.
  • Figure 6 is a schematic structural diagram of a computing device provided by an embodiment of the present application.
  • Figure 7 is a schematic structural diagram of a computing device cluster provided by an embodiment of the present application.
  • Figure 8 is a schematic structural diagram of another computing device cluster provided by an embodiment of the present application.
  • Figure 9 is a schematic structural diagram of another computing device cluster provided by an embodiment of the present application.
  • first and second in the embodiments of this application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, features defined as “first” and “second” may explicitly or implicitly include one or more of these features.
  • Resource pool A collection of various hardware and software involved in cloud computing data centers.
  • the resources provided by the resource pool can be divided into computing resources, storage resources or network resources.
  • Cloud service providers can provide the above resources to users in the form of cloud services.
  • Dedicated host It is a service model in cloud services. In this service model, users can directly purchase the entire host instead of a virtual machine.
  • a virtual machine also called a virtual server, is a type of computer with complete hardware system functions simulated through software on the same host/physical server (PM) based on virtualization technology.
  • PM host/physical server
  • Dedicated hosts have the characteristics of exclusive physical resources and more flexible deployment. They do not share capacity with other customers and can control the deployment method of virtual machines on dedicated hosts.
  • Exclusive resource pool It is a collection of resources in the resource pool that are exclusive to users, including multi-dimensional resources such as computing, network, and storage, and are also isolated from other resources.
  • dedicated resource pools have the characteristics of high resource isolation and users have absolute control, more and more users try to use dedicated resource pools as their first choice when using cloud services. Specifically, users have absolute control over their own exclusive resource pools. For example, users can freely manage the resource distribution on the dedicated host cluster in the dedicated resource pool, and can even specify the host where the VM is deployed, as well as specify the parameters of the storage volume and network.
  • the resource management methods provided by cloud service vendors are relatively limited, making it difficult for the capacity management of dedicated resource pools to meet business needs and cost requirements. For example, when the business scale increases significantly, it is difficult for cloud service providers to promptly remind users to purchase more dedicated resources and increase the capacity of the dedicated resource pool to meet the growing business needs. For another example, when the resources in the dedicated resource pool are at low utilization levels for a long time, the cloud service provider does not remind users to reduce the purchased dedicated resources in order to reduce the capacity of the dedicated resource pool and reduce costs.
  • this application provides a capacity management method.
  • This method can be executed by the capacity management system on the cloud platform side.
  • the cloud platform is a platform built by cloud service vendors based on a large amount of hardware to provide computing resources, storage resources, and network resources in the form of cloud services.
  • the cloud platform can provide users with exclusive resource pool services.
  • the capacity management system is used to perform capacity management (for example, capacity scaling management) of the dedicated resource pool belonging to the user when the user uses the dedicated resource pool service.
  • the capacity management system can be a software system used to manage the capacity of a dedicated resource pool. This software system can be integrated into the cloud platform. Or used independently.
  • the capacity management system can be deployed in a computing device cluster, such as a cluster in a cloud computing data center.
  • the computing device cluster executes the program code of the software system, thereby executing the capacity management method.
  • the capacity management system may also be a hardware system, such as a computing device cluster with capacity management functions. When the hardware system is running, the capacity management method of this application is executed.
  • the capacity management system can obtain the resource usage of at least one dimension in the exclusive resource pool, and then determine the measurement value corresponding to the monitoring indicator item of the exclusive resource pool based on the resource usage of at least one dimension, and then determine the measurement value corresponding to the monitoring indicator item of the above-mentioned monitoring indicator item.
  • the measurement values and alarm thresholds corresponding to the monitoring indicator items determine whether the dedicated resource pool meets the capacity scaling conditions. When the dedicated resource pool meets the capacity scaling conditions, capacity scaling recommendations are presented to the user.
  • This method collects the resource usage in the dedicated resource pool and presents capacity scaling suggestions to the user when it is determined that the dedicated resource pool meets the capacity scaling conditions based on the resource usage, thereby reminding the user to purchase replacements as soon as possible when insufficient resources lead to a reduction in the amount that can be issued.
  • cloud service providers as resource providers, can calculate the dedicated resources required by users within the service cycle based on the business parameters input by users by collecting and analyzing the resource usage data of a large number of users when using exclusive resources. Type and quantity. Therefore, when users purchase dedicated resource pool services, users can be allowed to enter business parameters, and the capacity management system can guide users to specifically purchase dedicated resources such as the type and quantity of dedicated hosts to meet the user's business requirements. This solves the problem of users purchasing an unreasonable number of exclusive resources due to lack of knowledge or experience when purchasing exclusive resource pool services.
  • the capacity management system 10 includes a capacity management device 100.
  • the capacity management device 100 is used to perform capacity management on the dedicated resource pool belonging to the user when the user uses the dedicated resource pool service. .
  • the capacity management system 10 may also include a capacity recommendation device 200, which is used to recommend the type and quantity of dedicated resources to the user when purchasing a dedicated resource pool service.
  • the capacity recommendation device 100 is responsible for receiving service parameters input by the user, including but not limited to service type and core number, and then recommends the type and quantity of exclusive resources to be purchased to the user based on the service parameters, thereby meeting the user's needs.
  • the capacity management device 300 may be responsible for helping the user perform resource management on the dedicated resource pool formed by purchasing the above dedicated resources. For example, the capacity management device 300 can calculate the number of virtual machines that can be allocated by the remaining resources of the dedicated resource pool (this process is also called capacity calculation), so as to issue an alarm when the capacity is insufficient.
  • the capacity management device 200 can also determine whether the dedicated resource pool is in a low-load operation state based on indicators set by the user, and suggest the user to reduce the capacity of the dedicated resource pool when the load is low.
  • the capacity recommendation device 100 is configured to receive a dedicated resource pool creation request, which includes service parameters input by the user, and then determines the capacity recommendation device 100 according to the service type in the service parameters and the specifications of the virtual machine used to implement the service. , determine the type of dedicated host, and then determine the number of dedicated hosts of the corresponding type based on the number of virtual machines in the business parameters, and recommend the type and number of dedicated hosts to the user.
  • the capacity management device 200 is configured to obtain the resource usage of at least one dimension in the dedicated resource pool, determine the measurement value corresponding to the monitoring indicator item of the dedicated resource pool based on the resource usage of at least one dimension, and then determine the measurement value according to the monitoring indicator.
  • the measurement value of the item and the alarm threshold corresponding to the monitoring indicator item determine whether the dedicated resource pool meets the capacity scaling conditions.
  • capacity recommendation device 100 The functions and specific implementation of the capacity recommendation device 100 and the capacity management device 200 will be described in detail below.
  • the capacity recommendation device 100 is mainly responsible for receiving a dedicated resource pool creation request input by the user when creating a dedicated resource pool.
  • the dedicated resource pool creation request is a request related to the business.
  • the dedicated resource pool creation request carries business parameters input by the user.
  • the business parameters Including this time
  • the service parameters also include the service type and the specifications of the virtual machine used by the user.
  • the business type represents the functions planned to be implemented using the dedicated resource pool feature.
  • the business type can be Redis or Nginx.
  • the specifications of the virtual machine refer to the model of the virtual machine.
  • the specifications of the virtual machine can include 16U32G or c7.8xlarge.2.
  • the business parameters can also include the estimated total number of virtual machines, the number of virtual machines that the user creates for the application this time, or the subsequent number of virtual machines that the user may need due to increased load during the entire life cycle of the application. Apply the number of newly created virtual machines. If the user does not enter the estimated total number of virtual machines, it can also be estimated based on the historical total number of virtual machines of similar services.
  • the capacity recommendation device 100 can estimate the type and quantity of the dedicated resources that the user needs to purchase.
  • the type and quantity of exclusive resources that users need to purchase please refer to the following formula:
  • Demand j is the total amount of virtual machines that need to be added on resource j input by the user.
  • Demand j for five 4U8G VMs is 40.
  • Future j is the total amount of virtual machines on resource j that is expected to be used in the future input by the user.
  • ⁇ j is the correction coefficient of Future j .
  • the type of dedicated resource (such as a dedicated host) is selected for the user based on past data experience.
  • f(Business, VM_type) is the experience choice of experts who choose dedicated host types.
  • Resource i,j is the number of dedicated resources of type i in resource dimension j.
  • the value of a host including 48 virtual central processing units (virtual CPUs, vCPUs) in the CPU dimension is 48.
  • ⁇ i is the correction coefficient of the final calculated number of dedicated resources.
  • the calculation logic of the above formula is: the user enters the total amount of each resource type that needs to be purchased this time and the expected future amount, such as how many cores, how much memory, etc. are needed. Among them, the expected future amount needs to be corrected by a coefficient, which is generally 0.7-0.9.
  • the capacity recommendation device 100 first selects the type of dedicated resources based on the service type input by the user and the specifications of the virtual machine, and based on expert experience. Then calculate the required number of dedicated resources in each dimension of the resource. Finally, select the number of required dedicated resources among all dimensional resources. The number required by the largest dimension is the number of dedicated resources.
  • the type and quantity of dedicated resources such as dedicated hosts are corrected by the correction coefficient. After recommending it to users, the correction coefficient can generally be set to 1.05-1.2.
  • the capacity management device 200 is responsible for inputting the indicators of the dedicated resource clusters that the user is interested in after purchasing the dedicated resource pool to inform the capacity management device 100 how to perform resource management.
  • the indicators input by the user may include a virtual machine list, and the virtual machine list records at least one virtual machine that the user is concerned about.
  • the capacity management device 100 can issue an early warning.
  • the indicators input by the user may also include alarm thresholds corresponding to the monitoring indicator items.
  • the monitoring indicator item includes the issuable number of the virtual machines that the user is concerned about
  • the indicators input by the user may also include the alarm threshold for the issuable number of the virtual machines, which is also called the remaining virtual machine threshold and the first alarm threshold.
  • the capacity management device 100 may send an alarm to the user.
  • the indicators input by the user may also include the proportion of virtual machines that the user is concerned about, such as the proportion of VMs that the user is concerned about.
  • users can enter their own dedicated resource pool, and the expected number of VMs that can be issued can be understood as the minimum unit. For example, if a user needs 8 8xlarge.2, 5 4xlarge.2, or 10 2xlarge.2 virtual machines to execute their business, the user can enter the model (VM specification) and quantity of the above virtual machines.
  • the capacity management device 100 can calculate the capacity of the virtual machine list and allocation ratio input by the user, perform real-time monitoring of the monitoring indicator items that the user is concerned about, and provide an expansion warning to the user when the capacity is insufficient; when the resource usage rate of the dedicated resource pool is relatively high, When it is low, users are advised to scale down.
  • the basic method of capacity calculation is: the user first inputs the VM type and issuance ratio that he wants to know, and then the number of VMs that the user cares about is calculated based on the resource usage in the current dedicated resource pool.
  • the calculation formula is as follows:
  • a i,j is the remaining resource amount in the jth dimension of the exclusive resource i purchased by the user (which can be determined by the total amount of purchased resources and resource usage).
  • ⁇ k represents the provisioning ratio of different virtual machines in the virtual machine list input by the user. For example, if you input [8 8xlarge.2,5 4xlarge.2,10 2xlarge.2], the value of ⁇ k is 8,5,10.
  • r k,j represents the number of jth-dimensional resources of different virtual machines in the virtual machine list input by the user. In the above example, the value of r k,j in the vCPU dimension is 32,16,8.
  • b j is the sum of j-dimensional resources in the virtual machine list that the user is interested in input by the user.
  • S i is the number of VMs that can be issued in the user's exclusive resource i according to the issuance ratio input by the user.
  • S′ i,k is the number of k-th virtual machines that can still be allocated the remaining resources after the dedicated resource i is allocated proportionally to the total resources of all virtual machines in the virtual machine list entered by the user in a certain dimension.
  • the calculation logic is as follows: the capacity management device 100 calculates the amount of resources in each dimension required by the VMs in the list based on the list of virtual machines that the user inputs and is of interest to, including the number of VMs and VM specifications. Then, in each dedicated resource, calculate the number of VMs that can be issued. For the remaining space after resource allocation, the allocable quantity of each VM in the list can be calculated one by one, and then the allocable quantity can be accumulated.
  • One function of the capacity management device 100 is to provide scaling recommendations (capacity expansion warnings or capacity reduction recommendations) for a dedicated resource pool.
  • Users can control the generation of early warnings by setting the criteria for warning triggering.
  • the user's input is after the number of VMs he cares about is reduced to a certain value.
  • the user can specify that when the number of VMs of the 8xlarge.2 specification in the cluster that can be issued is less than 5, and the number of VMs of the 4xlarge.2 specification can be issued.
  • An early warning is triggered when the number is less than 10.
  • the specific number of VMs that can be issued can be obtained from the results of capacity calculation.
  • the recommended usage method of scaling down is similar to scaling up.
  • the purpose is to help users reduce resource usage when the resource usage in the cluster continues to be in a low state.
  • users can configure: when the resource usage of a certain resource in the cluster continues to be lower than a certain threshold for a window period, scaling down recommendations will be made to the user. For example, users can configure scaling recommendations when the vCPU resource usage in the cluster continues to be lower than 30% for 3 hours.
  • the calculation method of resource usage in the cluster is:
  • ⁇ j is the usage rate of resource dimension j
  • b k j is the j-th dimension resource usage quantity of VM k purchased by the user
  • a i, j is the total amount of j-th dimension resource of exclusive resource i purchased by the user.
  • This application constructs a set of capacity calculation formulas through the capacity recommendation device 200 when the user creates an exclusive resource pool in the exclusive resource pool service, and converts the business parameters input by the user into exclusive resources (such as exclusive hosts) that the user is recommended to purchase.
  • exclusive resources such as exclusive hosts
  • the type and quantity provide guidance for users to create exclusive resource pools.
  • a set of capacity management device 100 is also provided to help the user manage the capacity of the dedicated resource pool.
  • the capacity management device 100 can help users make capacity warnings or reduce capacity recommendations, reduce users' inconvenience in cluster capacity management, and improve user experience.
  • an embodiment of the present application also provides a capacity management method.
  • the capacity management method of the embodiment of the present application is introduced below with reference to the accompanying drawings.
  • the method includes:
  • the capacity recommendation device 200 receives a resource pool creation request.
  • the dedicated resource pool creation request includes the business parameters entered by the user.
  • Service parameters are specifically parameters related to user services, including but not limited to service type, specifications of virtual machines used to implement services, and the number of virtual machines.
  • the virtual machine is the basic unit that encapsulates resources to achieve isolation.
  • the virtual machine can be implemented through virtualization technology.
  • the number of virtual machines can include the number of virtual machines that need to be added this time.
  • the number of virtual machines can also include the total number of virtual machines or the number of virtual machines that need to be added when the load increases. Later, during the entire life cycle of the application, due to the increase in load, users may create new virtual machines for this application. Therefore, users can configure the number of virtual machines that need to be added when the load increases.
  • the capacity recommendation device 200 may refer to relevant indicators of similar services in history.
  • the dedicated resource pool creation interface 300 includes a business parameter configuration component 302 and a submission component 304.
  • the business parameter configuration component 302 includes the configuration control for the number of VMs that need to be added this time 3022 and the total number of VMs configuration control 3024, the configuration control for the number of VMs needed this time created by the user for the application 3026, and the subsequent configuration control for the number of new VMs for the application 3028 , the user can use the above configuration controls to separately configure the number of VMs to be added this time, the estimated total number of VMs (that is, the total number of VMs), the number of VMs required this time created by the user for the application, and the subsequent full life of the application.
  • the submission component 304 includes a submission control 3042 and a cancellation control 3044.
  • the user triggers the submission control 3042 the above business parameters configured by the user can be submitted.
  • the cancellation control 3044 the configuration can be canceled.
  • the capacity recommendation device 200 determines the type of dedicated host based on the service type in the service parameters and the specifications of the virtual machine used to implement the service.
  • f can be selected based on expert experience. For some common applications such as Redis, Nginx, MySQL, etc., some dedicated hosts with larger host capacity, higher CPU frequency, and multi-channel memory will be selected based on experience; for some applications with more communication, CPU density will be given priority. High, dedicated host with large communication bandwidth.
  • the capacity recommendation device 200 determines the number of dedicated hosts of the corresponding type according to the number of resource isolation units in the service parameters.
  • the capacity recommendation device 200 can be based on the formula (1) And the number of resource isolation units in the business parameters determines the number of dedicated hosts of the corresponding type. For example, the capacity recommendation device 200 can substitute the number of virtual machines in the service parameters, such as the number of VMs, into the equation (1) above. Thereby obtaining the number of dedicated hosts of the corresponding type.
  • the capacity recommendation device 200 recommends the type and quantity of the dedicated hosts to the user.
  • the capacity recommendation device 200 can display the type and quantity of dedicated hosts to the user through the result display interface, thereby recommending the above types of dedicated hosts to the user, as well as the recommended quantity to purchase, and thereby guiding the user to purchase reasonable dedicated resources to avoid Resources are wasted or it is difficult to meet requirements.
  • the capacity management device 100 obtains the resource usage of at least one dimension in the exclusive resource pool purchased by the user.
  • the capacity management device 100 can obtain the resource usage of at least one dimension (for example, each dimension) in the dedicated resource pool purchased by the user.
  • the dimension can be computing, storage or network (bandwidth).
  • the capacity management device 100 determines the measurement value corresponding to the monitoring indicator item of the dedicated resource pool based on the resource usage of the at least one dimension.
  • the capacity management apparatus 100 may determine the number of virtual machines that can be allocated by the remaining resources of the dedicated resource pool based on the total amount of resources in at least one dimension and the resource usage in at least one dimension in the dedicated resource pool.
  • the capacity management device 100 may determine the remaining resource amount in at least one dimension based on the resource usage in at least one dimension and the total amount of purchased resources in at least one dimension, and then determine the remaining resource amount in at least one dimension based on the remaining resource amount in at least one dimension and the virtual machine in at least one dimension.
  • the resource demand of the dimension determines the number of virtual machines that can be issued from the remaining resources of the dedicated resource pool.
  • the capacity management device 100 can also support the user in configuring the virtual machines that the user is interested in. Specifically, the capacity management device 100 receives a virtual machine list configured by the user through the capacity management interface. The virtual machine list records at least one virtual machine that the user is concerned about. Correspondingly, the capacity management device 100 can configure the virtual machine according to at least one virtual machine in the virtual machine list. The specifications determine the resource requirements of at least one virtual machine in at least one dimension. After obtaining the resource demand of the virtual machine that the user is paying attention to in at least one dimension, the capacity management device 100 can determine the resource demand of the dedicated resource pool based on the resource amount of at least one dimension in the capacity resource pool and the resource demand of the virtual machine in at least one dimension. The number of virtual machines that can be allocated with remaining resources.
  • the capacity management device 100 also supports the user to configure the distribution proportions of multiple virtual machines that the user is concerned about.
  • the capacity management device 100 can receive multiple virtual machines configured by the user through the capacity management interface.
  • the distribution ratio of machines can be characterized by the number of each virtual machine.
  • the capacity management device 100 supports the model and quantity of virtual machines configured by the user through the capacity management interface, and the model and quantity of the virtual machines are recorded in the virtual machine list.
  • the embodiment of this application also provides an example of a virtual machine list:
  • the first column in Table 1 is the model of the virtual machine
  • the second column in Table 1 is the number of virtual machines of the corresponding model. Based on this, the distribution proportion of virtual machines with models 8xlarge.2, 4xlarge.2, and 2xlarge.2 It could be 8:5:10.
  • the capacity management device 100 may also combine the above allocation ratio when determining the number of virtual machines that can be allocated from the remaining resources of the dedicated resource pool. Specifically, the capacity management device 100 can determine the dedicated resources to be distributed according to the distribution ratio based on the remaining resource amount in at least one dimension of the dedicated resource pool, the resource demand of multiple virtual machines in at least one dimension, and the issuance ratio of the multiple virtual machines. The number of virtual machines that can be allocated by the remaining resources of the pool.
  • the process by which the capacity management device 100 determines the number of virtual machines that can be allocated from the remaining resources of the dedicated resource pool can refer to the above formulas (2), (3), and (4), which will not be described again here.
  • the capacity management apparatus 100 may determine the resource usage rate of at least one dimension based on the total amount of resources in at least one dimension and the resource usage of at least one dimension in the dedicated resource pool. Referring to the above formula (5), for any dimension, the capacity management device 100 can accumulate the resource usage and purchase amount of each virtual machine in that dimension, and then determine the ratio of the cumulative resource usage to the cumulative resource purchase amount, so as to Determine resource usage for this dimension.
  • S212 The capacity management device 100 determines whether the dedicated resource pool meets the capacity expansion condition based on the measured value of the monitoring indicator item and the alarm threshold corresponding to the monitoring indicator item. When the dedicated resource pool meets the capacity scaling conditions, S214 is executed.
  • Capacity scaling conditions may include one of capacity expansion conditions or capacity reduction conditions.
  • the expansion conditions or shrinking conditions can be set by the user.
  • users can configure the monitoring indicator items during capacity expansion and the first alarm threshold corresponding to the monitoring indicator items through the capacity management interface, thereby setting expansion conditions.
  • the monitoring indicator item during capacity expansion may be the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool, for example, the number of virtual machines that can be issued that the user is concerned about.
  • the user can configure the monitoring indicator item during capacity reduction and the second alarm threshold corresponding to the monitoring indicator item through the capacity management interface, thereby setting the reduction conditions.
  • the monitoring indicator item during scaling down may be resource usage, for example, resource usage in at least one dimension.
  • the capacity management device 100 can compare the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool with the first alarm threshold. When the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool is less than the first alarm threshold, it indicates that the dedicated resource pool Meet the expansion conditions in the capacity expansion conditions.
  • the capacity management device 100 may compare the resource usage in at least one dimension with the second alarm threshold corresponding to the resource usage in at least one dimension, thereby determining whether the dedicated resource pool meets the capacity scaling condition. For example, if the resource usage of at least one dimension continues to be less than the second alarm threshold in a time window, it indicates that the dedicated resource pool meets the scaling conditions in the capacity scaling conditions.
  • the capacity management interface 400 includes a capacity expansion monitoring configuration component 402, a capacity reduction monitoring configuration component 404, and a submission component 406.
  • the capacity expansion monitoring configuration component 402 and the capacity reduction monitoring configuration component 404 are respectively It includes the corresponding monitoring indicator configuration control and threshold configuration control, specifically the expansion monitoring indicator configuration control 4022, the expansion alarm threshold configuration control 4024, the reduction monitoring indicator configuration control 4042, and the reduction alarm threshold configuration control 4044.
  • the expansion monitoring configuration component 402 may also include a focus list configuration control 4026 and a focus ratio configuration control 4028.
  • the submission can be completed through the submission control 4062 in the submission component 406. It should be noted that the user can also cancel the submission through the cancellation control 4064 in the submission component 406.
  • S214 The capacity management device 100 presents capacity expansion and contraction suggestions to the user.
  • Scaling recommendations include suggestions to remind users to expand or shrink capacity. Scaling recommendations can also include increasing or decreasing capacity.
  • the capacity expansion can be determined based on the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool and the first alarm threshold.
  • the amount of shrinkage can be determined based on resource usage and the second alarm threshold.
  • the above-mentioned S202 to S208 are optional steps in the embodiment of the present application, and the above-mentioned S202 to S208 may not be executed when performing the capacity management method in the embodiment of the present application.
  • users can also decide on their own the type and quantity of dedicated hosts they need to purchase based on their own experience.
  • the capacity management method provided by the embodiment of the present application can use the capacity management device 100 to help the user perform capacity management after the user purchases a dedicated resource pool service, including calculating the issuable quantity and providing capacity scaling suggestions, etc., so that the user can Know the amount information that can be issued when using it, and allow users to set the first alarm threshold for insufficient capacity, or when the resource usage does not reach the corresponding When the second alarm threshold is reached, scaling down is recommended.
  • this method also supports users to input business parameters when purchasing an exclusive resource pool, so that the capacity recommendation device 200 can help the user calculate the amount of resources that may need to be purchased in this service. Under the condition that the user's usage needs are met, It can guide users to make reasonable purchases, avoid resource waste, and save user costs. And compared with the unguided exclusive resource purchase method, the user experience can be greatly improved.
  • This scenario includes capacity management in the purchase phase and usage phase.
  • the user can interact with the capacity recommendation device 200 .
  • the user inputs service parameters, such as service type, specifications of virtual machines used to implement the service, number of virtual machines, etc.
  • the capacity recommendation device 200 receives the service parameters input by the user and calculates the type of exclusive resources that the user needs to purchase and the quantity of each exclusive resource in the background. Among them, the capacity recommendation device 200 calculates the type and quantity (amount of resources) of dedicated resources that the user needs to use based on experience or expert rules and the conversion formula from virtual machines to dedicated resources, and then feeds back the recommended values to the user. For example, the user inputs that his business is Redis and requires a VM with a total core count of 500 cores and 32U. The capacity recommendation device 200 can calculate that the user may need 10 dedicated hosts of a certain specification. Users can make exclusive resource purchase decisions based on the recommendation results.
  • the capacity management device 100 can be used.
  • the capacity management interface in addition to seeing the basic resource status of the cluster (such as resource usage and remaining resources in each dimension), you can also set the virtual machines you care about and their issuance proportions, and adjust the provisioning ratio of the virtual machines based on this proportion. Calculate the quantity. The result of the calculation is how many VMs can be allocated based on the remaining dedicated resources according to this ratio.
  • the capacity management device 100 can also allow the user to set different alarm thresholds on the capacity management interface. For example, when the value of 4xlarge.2VM that can be issued by the cluster is lower than 10, the user is notified to expand the capacity.
  • This application also provides a capacity management system 10.
  • the capacity management system 10 is deployed on the cloud platform side.
  • the cloud platform provides exclusive resource pool services to users.
  • the container management system 10 is used in the process of users using the exclusive resource pool services. Capacity management of user-specific resource pools.
  • the capacity management system 10 includes a capacity management device 100.
  • the capacity management device 100 includes:
  • the acquisition module 101 is used to obtain the resource usage of at least one dimension in the exclusive resource pool;
  • the monitoring module 103 is configured to determine the measurement value corresponding to the monitoring indicator item of the exclusive resource pool based on the resource usage of the at least one dimension;
  • the alarm module 105 is configured to determine whether the dedicated resource pool meets the capacity scaling condition based on the measured value of the monitoring indicator item and the alarm threshold corresponding to the monitoring indicator item. When the dedicated resource pool meets the capacity scaling condition , the user is presented with capacity scaling suggestions.
  • the above-mentioned capacity management device 100 can be implemented by hardware, or can be implemented by software.
  • the capacity management device 100 may be an application program running on a computing device, such as a computing engine.
  • the application can be provided to users as a virtualized service.
  • Virtualization services can include virtual machine VM services, bare metal server (bare metal server, BMS) services, and container (container) services.
  • the VM service can be a service that uses virtualization technology to virtualize a virtual machine resource pool on multiple physical hosts (such as computing devices) to provide users with VMs for use on demand.
  • the BMS service is a service that virtualizes BMS resource pools on multiple physical hosts to provide users with BMS on demand.
  • Container service is a service that virtualizes container resource pools on multiple physical hosts to provide users with containers on demand.
  • VM is a simulated virtual computer, that is, a logical computer.
  • BMS is an elastically scalable high-performance computing service. Its computing performance is the same as that of traditional physical machines, and it has the characteristics of safe physical isolation.
  • Containers are a kernel virtualization technology that can provide lightweight virtualization to isolate user space, processes and resources. It should be understood that the VM service, BMS service and container service in the above virtualization services are only specific examples. In actual applications, the virtualization service can also be other lightweight or heavyweight virtualization services, which are not discussed here. Specific limitations.
  • the capacity management device 100 may include at least one computing device, such as a server.
  • the capacity management device 100 may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD).
  • ASIC application-specific integrated circuit
  • PLD programmable logic device
  • the above-mentioned PLD can be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a general-purpose Array logic (generic array logic, GAL) or any combination thereof.
  • CPLD complex programmable logical device
  • FPGA field-programmable gate array
  • GAL general-purpose Array logic
  • the acquisition module 101, the monitoring module 103 or the alarm module 105 in the capacity management device 100 can also be implemented by software or hardware.
  • the acquisition module 101, the monitoring module 103 or the alarm module 105 may be an application program running on a computing device, such as a computing engine.
  • the acquisition module 101, the monitoring module 103 or the alarm module 105 may include at least one computing device, such as a server.
  • the acquisition module 101, the monitoring module 103 or the alarm module 105 can also be a device implemented using an application specific integrated circuit (ASIC) or a programmable logic device (PLD).
  • ASIC application specific integrated circuit
  • PLD programmable logic device
  • the monitoring indicator items include one or more of the number of virtual machines that can be allocated by the remaining resources of the dedicated resource pool or the resource usage rate.
  • the monitoring indicator item includes the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool;
  • the monitoring module 103 is specifically used for:
  • the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool is determined based on the amount of remaining resources in at least one dimension of the dedicated resource pool and the resource demand of the virtual machines in at least one dimension.
  • the device 100 further includes:
  • Configuration module 107 configured to receive a virtual machine list configured by the user through the capacity management interface, where the virtual machine list records at least one virtual machine that the user is concerned about;
  • the monitoring module 103 is also used to:
  • the virtual machine list records multiple virtual machines that the user is interested in;
  • the configuration module 107 is also used to:
  • the monitoring module 103 is specifically used for:
  • the resource demand of the multiple virtual machines in at least one dimension, and the issuance ratio of the multiple virtual machines determine the amount of resources when issuing according to the issuance ratio.
  • the monitoring indicator items include resource usage
  • the monitoring module 103 is specifically used for:
  • the resource usage rate of the at least one dimension is determined based on the total amount of resources of at least one dimension in the dedicated resource pool and the resource usage of the at least one dimension.
  • the system 10 further includes a capacity recommendation device 200.
  • the capacity recommendation device 200 includes:
  • the communication module 201 is configured to receive a dedicated resource pool creation request, where the dedicated resource pool creation request includes business parameters input by the user;
  • the determination module 203 is used to determine the type of the dedicated host according to the service type in the service parameters and the specifications of the virtual machine used to implement the service;
  • the determination module 203 is also used to determine the number of dedicated hosts of the corresponding type according to the number of virtual machines in the business parameters;
  • the recommendation module 205 is used to recommend the type and quantity of the dedicated hosts to the user.
  • the number of virtual machines in the service parameters includes the number of virtual machines that need to be added this time.
  • the number of virtual machines in the service parameters also includes the total number of virtual machines or the number of virtual machines that need to be added when the load increases.
  • computing device 600 includes: bus 602, processor 604, memory 606, and communication interface 608.
  • the processor 604, the memory 606 and the communication interface 608 communicate through the bus 602.
  • Computing device 600 may be a server or a terminal device. It should be understood that this application does not limit the number of processors and memories in the computing device 600.
  • Bus 602 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture. (extended industry standard architecture, EISA) bus, etc.
  • PCI peripheral component interconnect
  • EISA extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus, etc. For ease of presentation, only one line is used in Figure 6, but it does not mean that there is only one bus or one type of bus.
  • Bus 602 may include a path that carries information between various components of computing device 600 (eg, memory 606, processor 604, communications interface 608).
  • the processor 604 may include a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP) or a digital signal processor (DSP). any one or more of them.
  • CPU central processing unit
  • GPU graphics processing unit
  • MP microprocessor
  • DSP digital signal processor
  • Memory 606 may include volatile memory, such as random access memory (RAM). Memory 606 may also include non-volatile memory (non-volatile memory), such as read-only memory (ROM), flash memory, mechanical hard disk (hard disk drive, HDD) or solid state drive (solid state drive) ,SSD).
  • RAM random access memory
  • Memory 606 may also include non-volatile memory (non-volatile memory), such as read-only memory (ROM), flash memory, mechanical hard disk (hard disk drive, HDD) or solid state drive (solid state drive) ,SSD).
  • ROM read-only memory
  • flash memory such as hard disk (hard disk drive, HDD) or solid state drive (solid state drive) ,SSD).
  • SSD solid state drive
  • the memory 606 stores executable program code, and the processor 604 executes the executable program code to implement the aforementioned capacity management method. Specifically, the memory 606 stores instructions for the capacity management system 10 to execute the capacity management method.
  • the communication interface 608 uses transceiver modules such as, but not limited to, network interface cards and transceivers to implement communication between the computing device 600 and other devices or communication networks.
  • An embodiment of the present application also provides a computing device cluster.
  • the computing device cluster includes at least one computing device.
  • the computing device may be a server, such as a central server, an edge server, or a local server in a local data center.
  • the computing device may also be a terminal device such as a desktop computer, a laptop computer, or a smartphone.
  • the computing device cluster includes at least one computing device 600 .
  • Instructions for the same capacity management system 10 to perform the capacity management method may be stored in the memory 606 of one or more computing devices 600 in the cluster of computing devices.
  • one or more computing devices 600 in the computing device cluster may also be used to execute part of the instructions of the capacity management system 10 for executing the capacity management method.
  • a combination of one or more computing devices 600 may collectively execute instructions of the capacity management system 10 for performing the capacity management method.
  • the memory 606 in different computing devices 600 in the computing device cluster may store different instructions for executing part of the functions of the capacity management system 10 .
  • Figure 8 shows a possible implementation. As shown in FIG. 8 , two computing devices 600A and 600B are connected through a communication interface 608 . Stored on memory in computing device 600A are instructions for performing the functions of capacity management device 100 . Stored on memory in computing device 600B are instructions for performing the functions of capacity management device 100 . In other words, memory 606 of computing devices 600A and 600B collectively stores instructions for capacity management system 10 to perform the capacity management method.
  • connection method between computing device clusters shown in Figure 8 can be based on the fact that the capacity management method provided by this application requires a large amount of calculations to deduce the type and quantity of dedicated hosts that the user needs to purchase. Therefore, it is considered that the functions implemented by the capacity recommendation device 200 are performed by the computing device 600B.
  • computing device 600A shown in FIG. 8 may also be performed by multiple computing devices 600.
  • the functions of computing device 600B may also be performed by multiple computing devices 600 .
  • one or more computing devices in a cluster of computing devices may be connected through a network.
  • the network may be a wide area network or a local area network, etc.
  • Figure 9 shows a possible implementation. As shown in Figure 9, two computing devices 600C and 600D are connected through a network. Specifically, the connection to the network is made through a communication interface in each computing device.
  • the memory 606 in the computing device 600C stores instructions for performing the functions of the capacity management device 100 . At the same time, instructions for performing the functions of the capacity recommendation device 200 are stored in the memory 606 of the computing device 600D.
  • connection method between computing device clusters shown in Figure 9 can be: Considering that the capacity management method provided by this application requires a large amount of calculations to deduce the type and number of dedicated hosts that the user needs to purchase, the functions implemented by the capacity recommendation device 200 are considered handed over to the computing device 600D for execution.
  • computing device 600C shown in FIG. 9 may also be performed by multiple computing devices 600.
  • computing device 600D may also be performed by multiple computing devices 600.
  • An embodiment of the present application also provides a computer-readable storage medium.
  • the computer-readable storage medium may be any available medium that a computing device can store or a data storage device such as a data center that contains one or more available media.
  • the usable media may be magnetic media (eg, floppy disk, hard disk, tape), optical media (eg, DVD), or semiconductor media (eg, solid state drive), etc.
  • the computer-readable storage medium includes instructions that instruct the computing device to execute the above-described application to the capacity management system 10 for performing the capacity management method.
  • An embodiment of the present application also provides a computer program product containing instructions.
  • the computer program product may be a software or program product containing instructions capable of running on a computing device or stored in any available medium.
  • the computer program product is run on at least one computing device, at least one computing device is caused to execute the above capacity management method.

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Debugging And Monitoring (AREA)

Abstract

The present application provides a capacity management method, comprising: a capacity management system acquires a resource usage amount of at least one dimension in a dedicated resource pool, determines a measured value of a monitoring indicator of a capacity resource pool according to the resource usage amount of the at least one dimension, determines, according to the measured value of the monitoring indicator and a warning threshold, whether the dedicated resource pool meets a capacity expansion/reduction condition, and presents the capacity expansion/reduction suggestion to a user when the condition is met. Thus, when the number of available resources is reduced due to insufficient resources, a user can be prompted to purchase more dedicated resources as soon as possible for capacity expansion, or when the resource utilization rate is low for a long time, the user is prompted that the capacity is excessive, and some of dedicated resources can be properly unsubscribed for capacity reduction, so that the problems of difficult capacity measurement and calculation and inconvenient capacity management caused by a large resource scale in subsequent use processes of dedicated resource pools are solved.

Description

一种容量管理方法及相关***Capacity management method and related system
本申请要求于2022年09月07日提交中国国家知识产权局、申请号为202211091597.6、发明名称为“容量管理的方法、装置、服务器及存储介质”的中国专利申请的优先权，以及要求于2023年01月16日提交中国国家知识产权局、申请号为202310064017.2、发明名称为“一种容量管理方法及相关***”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。This application requires the priority of the Chinese patent application submitted to the State Intellectual Property Office of China on September 7, 2022, with the application number 202211091597.6 and the invention title "Method, device, server and storage medium for capacity management", and the application is requested in 2023 The priority of the Chinese patent application filed with the State Intellectual Property Office of China on January 16, 2017, with application number 202310064017.2 and the invention title "A capacity management method and related system", the entire content of which is incorporated into this application by reference.
技术领域Technical field
本申请涉及云计算技术领域，尤其涉及一种容量管理方法、***、计算设备集群、计算机可读存储介质、计算机程序产品。This application relates to the field of cloud computing technology, and in particular, to a capacity management method, system, computing device cluster, computer-readable storage medium, and computer program product.
背景技术Background technique
随着云计算的不断发展，越来越多的云服务厂商推出了专属主机(Dedicated Host，DeH)服务。专属主机是云服务中的一种服务模式，用户可以直接购买整个主机而不是虚拟机。专属主机具有物理资源独享、部署更灵活等特点，不与其他用户共享容量，并且可以控制虚拟机(virtual machine，VM)在专属主机上的部署方法。With the continuous development of cloud computing, more and more cloud service vendors have launched dedicated host (Dedicated Host, DeH) services. Dedicated hosting is a service model in cloud services where users can directly purchase the entire host instead of a virtual machine. Dedicated hosts have the characteristics of exclusive physical resources and more flexible deployment. They do not share capacity with other users and can control the deployment method of virtual machines (VMs) on dedicated hosts.
为了满足更高级别的需求，一些云服务厂商还推出了专属资源池服务。专属资源池服务由于具有资源隔离度较高，用户具有绝对控制权等特点，成为了高阶用户部署服务时的首选。在专属资源池服务中，用户对属于自己的专属资源池有着绝对管控的权利。例如，用户可以自由管理专属主机集群上的资源分布，甚至可以指定VM具体部署在哪个主机上，以及每个硬盘和网络的具体参数。In order to meet higher-level needs, some cloud service vendors have also launched exclusive resource pool services. Dedicated resource pool services have become the first choice for high-end users when deploying services due to their high resource isolation and users' absolute control. In the exclusive resource pool service, users have absolute control over their own exclusive resource pool. For example, users can freely manage the resource distribution on a dedicated host cluster, and can even specify which host the VM is deployed on, as well as the specific parameters of each hard disk and network.
然而，业务规模通常是动态变化的，尤其是在业务规模大幅增长阶段，专属资源池的资源规模较大，如何对专属资源池进行容量管理以满足业务需求和成本要求成为亟待解决的问题。However, business scale usually changes dynamically. Especially in the stage of substantial growth in business scale, the resource scale of the dedicated resource pool is large. How to manage the capacity of the dedicated resource pool to meet business needs and cost requirements has become an urgent problem to be solved.
发明内容Contents of the invention
本申请提供了一种容量管理方法，该方法通过收集专属资源池中资源使用情况，并在根据资源使用情况确定专属资源池满足容量伸缩条件时向用户呈现容量伸缩建议，从而实现在资源不足导致可发放量减少时提醒用户尽快购买更多专属资源进行扩容，或者在资源使用率长期处于低水平时提醒用户可能容量过剩，可以适当退订部分专属资源进行缩容，如此解决了专属资源池的后续使用过程中因资源规模较大而造成的容量测算困难、容量管理不便的问题，能够满足业务需求和成本要求。本申请还提供了上述方法对应的***、计算设备集群、计算机可读存储介质以及计算机程序产品。This application provides a capacity management method that collects resource usage in a dedicated resource pool and presents capacity scaling suggestions to the user when it is determined that the dedicated resource pool meets the capacity scaling conditions based on the resource usage, thereby achieving the goal of solving the problem caused by insufficient resources. When the issuable amount is reduced, users are reminded to purchase more exclusive resources as soon as possible to expand the capacity, or when resource usage is at a low level for a long time, users are reminded that there may be excess capacity and can appropriately unsubscribe from some exclusive resources to reduce capacity, thus solving the problem of exclusive resource pools. In the subsequent use process, the problems of difficulty in capacity measurement and inconvenience in capacity management caused by the large scale of resources can be solved to meet business needs and cost requirements. This application also provides systems, computing device clusters, computer-readable storage media and computer program products corresponding to the above methods.
第一方面，本申请提供一种容量管理方法。该方法可以由云平台侧的容量管理***执行。云平台向用户提供专属资源池服务，容器管理***用于在所述用户使用所述专属资源池服务的过程中对属于所述用户的专属资源池进行容量管理。In a first aspect, this application provides a capacity management method. This method can be executed by the capacity management system on the cloud platform side. The cloud platform provides exclusive resource pool services to users, and the container management system is used to perform capacity management on the exclusive resource pool belonging to the user when the user uses the exclusive resource pool service.
容量管理***可以是软件***，该软件***可以集成在云平台，或者是独立使用。容量管理***可以部署在计算设备集群，例如是云计算数据中心的集群，计算设备集群执行软件***的程序代码，从而执行容量管理方法。容量管理***也可以是硬件***，例如是具有容量管理功能的计算设备集群。该硬件***运行时执行本申请的容量管理方法。The capacity management system can be a software system, which can be integrated into the cloud platform or used independently. The capacity management system can be deployed in a computing device cluster, such as a cluster in a cloud computing data center. The computing device cluster executes the program code of the software system, thereby executing the capacity management method. The capacity management system may also be a hardware system, such as a cluster of computing devices with capacity management functions. When the hardware system is running, the capacity management method of this application is executed.
具体地，容量管理***获取专属资源池中至少一个维度的资源使用量，根据至少一个维度的资源使用量，确定专属资源池的监测指标项对应的测量值，根据监测指标项的测量值以及监测指标项对应的告警阈值，确定专属资源池是否满足容量伸缩条件，当所述专属资源池满足所述容量伸缩条件时，向所述用户呈现容量伸缩建议。Specifically, the capacity management system obtains the resource usage of at least one dimension in the exclusive resource pool, determines the measurement value corresponding to the monitoring indicator item of the exclusive resource pool based on the resource usage of at least one dimension, and determines the measurement value corresponding to the monitoring indicator item of the exclusive resource pool. The alarm threshold corresponding to the indicator item determines whether the dedicated resource pool meets the capacity scaling conditions. When the dedicated resource pool meets the capacity scaling conditions, capacity scaling suggestions are presented to the user.
该方法通过收集专属资源池中资源使用情况，并在根据资源使用情况确定专属资源池满足容量伸缩条件时向用户呈现容量伸缩建议，从而实现在资源不足导致可发放量减少时提醒用户尽快购买更多专属资源进行扩容，或者在资源使用率长期处于低水平时提醒用户可能容量过剩，可以适当退订部分专属资源进行缩容，如此解决了专属资源池的后续使用过程中因资源规模较大而造成的容量测算困难、容量管 理不便的问题。This method collects the resource usage in the dedicated resource pool and presents capacity scaling suggestions to the user when it is determined that the dedicated resource pool meets the capacity scaling conditions based on the resource usage, thereby reminding the user to purchase replacements as soon as possible when insufficient resources lead to a reduction in the amount that can be issued. To expand the capacity of multiple dedicated resources, or to remind users that there may be excess capacity when resource usage is at a low level for a long time, they can appropriately unsubscribe from some dedicated resources to reduce the capacity. This solves the problem of large resource scale during the subsequent use of the dedicated resource pool. Difficulties in capacity measurement and capacity management caused by Inconvenient issues to deal with.
在一些可能的实现方式中，监测指标项包括专属资源池的剩余资源能够发放的虚拟机数量或资源使用率中的一种或多种。其中，专属资源池的剩余资源能够发放的虚拟机数量也可以称作可发放数量。容量管理***通过对可发放数量进行监测，可以及时提醒用户扩容，通过对资源使用量进行监测，可以及时提醒用户缩容，降低成本。In some possible implementations, the monitoring indicator items include one or more of the number of virtual machines that can be allocated by the remaining resources of the dedicated resource pool or the resource usage rate. Among them, the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool can also be called the number that can be issued. The capacity management system can promptly remind users to expand capacity by monitoring the amount that can be issued, and by monitoring resource usage, it can promptly remind users to shrink capacity and reduce costs.
在一些可能的实现方式中，所述监控指标项所述包括专属资源池的剩余资源能够发放的虚拟机数量，相应地，容量管理***可以根据专属资源池中至少一个维度的资源总量以及至少一个维度的资源使用量，确定专属资源池中至少一个维度的剩余资源量，然后根据专属资源池中至少一个维度的剩余资源量以及虚拟机在至少一个维度的资源需求量，确定专属资源池的剩余资源能够发放的虚拟机数量。In some possible implementations, the monitoring indicator item includes the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool. Correspondingly, the capacity management system can be based on the total amount of resources in at least one dimension of the dedicated resource pool and at least Based on the resource usage in one dimension, determine the amount of remaining resources in at least one dimension in the dedicated resource pool, and then determine the amount of resources in the dedicated resource pool based on the amount of remaining resources in at least one dimension in the dedicated resource pool and the resource demand of the virtual machine in at least one dimension. The number of virtual machines that can be allocated with remaining resources.
该方法通过先确定剩余资源量，然后基于剩余资源量以及虚拟机在至少一个维度的资源需求量，可以比较准确地测算出剩余资源能够发放的虚拟机数量，基于该数量进行扩容告警具有较高可信度，能够满足业务需求。This method first determines the amount of remaining resources, and then based on the amount of remaining resources and the resource demand of the virtual machine in at least one dimension, it can more accurately calculate the number of virtual machines that can be issued with the remaining resources. Expansion alarms based on this number have higher Credibility and ability to meet business needs.
在一些可能的实现方式中，容量管理***还可以接收用户通过容量管理界面配置的虚拟机列表。该虚拟机列表记录有用户关注的至少一个虚拟机。然后容量管理***还可以根据虚拟机列表中至少一个虚拟机的规格确定至少一个虚拟机在至少一个维度的资源需求量。In some possible implementations, the capacity management system can also receive a list of virtual machines configured by users through the capacity management interface. The virtual machine list records at least one virtual machine that the user is concerned about. Then the capacity management system can also determine the resource requirement of at least one virtual machine in at least one dimension according to the specifications of at least one virtual machine in the virtual machine list.
如此可以实现对用户关注的虚拟机进行可发放数量的测算，从而能够满足用户的个性化需求。In this way, the number of virtual machines that the user is interested in can be calculated, thereby meeting the user's personalized needs.
在一些可能的实现方式中，虚拟机列表记录有用户关注的多个虚拟机。容量管理***还可以接收用户通过容量管理界面配置的多个虚拟机的发放比例。相应地，容量管理***可以根据所述专属资源池中至少一个维度的剩余资源量以及所述多个虚拟机在至少一个维度的资源需求量、所述多个虚拟机的发放比例，确定按照所述发放比例发放时所述专属资源池的剩余资源能够发放的虚拟机数量。In some possible implementations, the virtual machine list records multiple virtual machines that the user is interested in. The capacity management system can also receive the provisioning ratios of multiple virtual machines configured by users through the capacity management interface. Correspondingly, the capacity management system may determine the amount of resources remaining in the dedicated resource pool in at least one dimension, the resource requirements of the multiple virtual machines in at least one dimension, and the issuance ratio of the multiple virtual machines. The number of virtual machines that can be allocated from the remaining resources of the dedicated resource pool when the allocation ratio is allocated.
由于不同类型的虚拟机通常是按比例方法，因此，在测算虚拟机的可发放数量时，结合发放比例进行测算，能够提高测算结果的准确度，进而提高可靠性。Since different types of virtual machines are usually based on a proportional method, when calculating the number of virtual machines that can be issued, combining the provisioning ratio for calculation can improve the accuracy of the measurement results and thus improve the reliability.
在一些可能的实现方式中，所述监控指标项所述包括资源使用率。容量管理***可以根据所述专属资源池中至少一个维度的资源总量以及所述至少一个维度的资源使用量，确定所述至少一个维度的资源使用率。In some possible implementations, the monitoring indicator item includes resource usage. The capacity management system may determine the resource usage rate of the at least one dimension based on the total amount of resources of at least one dimension in the dedicated resource pool and the resource usage of the at least one dimension.
该方法基于专属资源池中至少一个维度的资源总量和至少一个维度的资源使用量，可以精准地确定至少一个维度的资源使用率，如此可以为缩容建议提供帮助。This method is based on the total amount of resources in at least one dimension and the resource usage in at least one dimension in the dedicated resource pool, and can accurately determine the resource usage in at least one dimension, which can provide help for scaling down recommendations.
在一些可能的实现方式中，容量管理***还可以接收专属资源池创建请求，该专属资源池创建请求中包括用户输入的业务参数。容量管理***可以根据业务参数中的业务类型和用于实现业务的虚拟机的规格，确定专属主机的类型，然后根据所述业务参数中的虚拟机数量，确定相应类型的专属主机的数量，接着向所述用户推荐所述专属主机的类型和数量。In some possible implementations, the capacity management system can also receive a dedicated resource pool creation request, where the dedicated resource pool creation request includes business parameters input by the user. The capacity management system can determine the type of dedicated host based on the service type in the service parameters and the specifications of the virtual machines used to implement the service, and then determine the number of dedicated hosts of the corresponding type based on the number of virtual machines in the service parameters, and then Recommend the type and quantity of the dedicated hosts to the user.
该方法支持在用户购买专属资源池服务时，允许用户输入业务参数，根据业务参数推荐用户具体购买专属资源如专属主机的类型、数量，以满足用户的业务的各项要求。由此解决用户在购买专属资源池服务时，因知识或经验欠缺导致的购买专属资源数量不合理的问题。This method supports allowing the user to input business parameters when purchasing exclusive resource pool services, and recommends the user to specifically purchase exclusive resources such as the type and quantity of exclusive hosts based on the business parameters to meet the user's business requirements. This solves the problem of users purchasing an unreasonable number of exclusive resources due to lack of knowledge or experience when purchasing exclusive resource pool services.
在一些可能的实现方式中，业务参数中的虚拟机数量包括本次需要添加的虚拟机数量。如此可以至少满足当前的业务需求。In some possible implementations, the number of virtual machines in the business parameters includes the number of virtual machines that need to be added this time. This can at least meet current business needs.
在一些可能的实现方式中，所述业务参数中的虚拟机数量还包括虚拟机总数量或负载增加时需要添加的虚拟机数量。如此可以满足全生命周期或后期负载增加时的业务需求。In some possible implementations, the number of virtual machines in the service parameters also includes the total number of virtual machines or the number of virtual machines that need to be added when the load increases. This can meet business needs during the entire life cycle or when the load increases later.
在一些可能的实现方式中，至少一个维度的资源包括计算资源、存储资源或网络资源，该方法通过对不同维度的资源分别进行统计、测算，并根据各维度的测算结果，确定最终的测算结果，可以提高测算结果的准确度。In some possible implementations, resources in at least one dimension include computing resources, storage resources, or network resources. This method performs statistics and calculations on resources in different dimensions, and determines the final calculation results based on the calculation results of each dimension. , which can improve the accuracy of the calculation results.
在一些可能的实现方式中，容量管理***还可以记录风险事件，该风险事件可以包括资源不足导致虚拟机发放失败，相应地，容量管理***还可以根据风险事件，调整告警阈值。例如，容量管理***可以根据风险事件，增加专属资源池的剩余资源能够发放的虚拟机数量对应的告警阈值。如此可以降低专属资源池后续使用过程中风险事件发生的概率。In some possible implementations, the capacity management system can also record risk events. The risk events can include failure of virtual machine provisioning due to insufficient resources. Correspondingly, the capacity management system can also adjust alarm thresholds based on risk events. For example, the capacity management system can increase the alarm threshold corresponding to the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool based on risk events. This can reduce the probability of risk events occurring during subsequent use of the dedicated resource pool.
第二方面，本申请提供一种容量管理***。容量管理***部署在云平台侧，云平台向用户提供专属 资源池服务，该容器管理***用于在用户使用所述专属资源池服务的过程中对属于用户的专属资源池进行容量管理。其中，容量管理***包括容量管理装置，该容量管理装置包括：In a second aspect, this application provides a capacity management system. The capacity management system is deployed on the cloud platform side, and the cloud platform provides users with exclusive Resource pool service, the container management system is used to perform capacity management on the exclusive resource pool belonging to the user when the user uses the exclusive resource pool service. Wherein, the capacity management system includes a capacity management device, and the capacity management device includes:
获取模块，用于获取所述专属资源池中至少一个维度的资源使用量；An acquisition module, used to acquire the resource usage of at least one dimension in the exclusive resource pool;
监测模块，用于根据所述至少一个维度的资源使用量，确定所述专属资源池的监测指标项对应的测量值；A monitoring module, configured to determine the measurement value corresponding to the monitoring indicator item of the exclusive resource pool based on the resource usage of the at least one dimension;
告警模块，用于根据所述监测指标项的测量值以及所述监测指标项对应的告警阈值，确定所述专属资源池是否满足容量伸缩条件，当所述专属资源池满足所述容量伸缩条件时，向所述用户呈现容量伸缩建议。An alarm module, configured to determine whether the dedicated resource pool meets the capacity scaling condition based on the measured value of the monitoring indicator item and the alarm threshold corresponding to the monitoring indicator item. When the dedicated resource pool meets the capacity scaling condition, , presenting capacity scaling suggestions to the user.
在一些可能的实现方式中，所述监测指标项包括所述专属资源池的剩余资源能够发放的虚拟机数量或资源使用率中的一种或多种。In some possible implementations, the monitoring indicator items include one or more of the number of virtual machines that can be allocated by the remaining resources of the dedicated resource pool or the resource usage rate.
在一些可能的实现方式中，所述监控指标项所述包括专属资源池的剩余资源能够发放的虚拟机数量；In some possible implementations, the monitoring indicator item includes the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool;
所述监测模块具体用于：The monitoring module is specifically used for:
根据所述专属资源池中至少一个维度的资源总量以及所述至少一个维度的资源使用量，确定所述专属资源池中至少一个维度的剩余资源量；Determine the remaining resource amount of at least one dimension in the exclusive resource pool according to the total amount of resources in at least one dimension in the exclusive resource pool and the resource usage in the at least one dimension;
根据所述专属资源池中至少一个维度的剩余资源量以及虚拟机在至少一个维度的资源需求量，确定所述专属资源池的剩余资源能够发放的虚拟机数量。The number of virtual machines that can be issued by the remaining resources of the dedicated resource pool is determined based on the amount of remaining resources in at least one dimension of the dedicated resource pool and the resource demand of the virtual machines in at least one dimension.
在一些可能的实现方式中，所述容量管理装置还包括：In some possible implementations, the capacity management device further includes:
配置模块，用于接收所述用户通过容量管理界面配置的虚拟机列表，所述虚拟机列表记录有所述用户关注的至少一个虚拟机；A configuration module configured to receive a virtual machine list configured by the user through the capacity management interface, where the virtual machine list records at least one virtual machine that the user is concerned about;
所述监测模块还用于：The monitoring module is also used to:
根据所述虚拟机列表中所述至少一个虚拟机的规格确定所述至少一个虚拟机在至少一个维度的资源需求量。Determine the resource requirement of the at least one virtual machine in at least one dimension according to the specifications of the at least one virtual machine in the virtual machine list.
在一些可能的实现方式中，所述虚拟机列表记录有所述用户关注的多个虚拟机；In some possible implementations, the virtual machine list records multiple virtual machines that the user is interested in;
所述配置模块还用于：The configuration module is also used to:
接收所述用户通过所述容量管理界面配置的所述多个虚拟机的发放比例；Receive the issuance ratio of the multiple virtual machines configured by the user through the capacity management interface;
所述监测模块具体用于：The monitoring module is specifically used for:
根据所述专属资源池中至少一个维度的剩余资源量以及所述多个虚拟机在至少一个维度的资源需求量、所述多个虚拟机的发放比例，确定按照所述发放比例发放时所述专属资源池的剩余资源能够发放的虚拟机数量。According to the remaining resource amount in at least one dimension of the dedicated resource pool, the resource demand of the multiple virtual machines in at least one dimension, and the issuance ratio of the multiple virtual machines, determine the amount of resources when issuing according to the issuance ratio. The number of virtual machines that can be allocated from the remaining resources of the dedicated resource pool.
在一些可能的实现方式中，所述监控指标项所述包括资源使用率；In some possible implementations, the monitoring indicator items include resource usage;
所述监测模块具体用于：The monitoring module is specifically used for:
根据所述专属资源池中至少一个维度的资源总量以及所述至少一个维度的资源使用量，确定所述至少一个维度的资源使用率。The resource usage rate of the at least one dimension is determined based on the total amount of resources of at least one dimension in the dedicated resource pool and the resource usage of the at least one dimension.
在一些可能的实现方式中，所述***还包括容量推荐装置，所述容量推荐装置包括：In some possible implementations, the system further includes a capacity recommendation device, and the capacity recommendation device includes:
通信模块，用于接收专属资源池创建请求，所述专属资源池创建请求中包括用户输入的业务参数；A communication module, configured to receive a dedicated resource pool creation request, where the dedicated resource pool creation request includes business parameters input by the user;
确定模块，用于根据所述业务参数中的业务类型和用于实现业务的虚拟机的规格，确定专属主机的类型；A determination module configured to determine the type of the dedicated host based on the service type in the service parameters and the specifications of the virtual machine used to implement the service;
所述确定模块，还用于根据所述业务参数中的虚拟机数量，确定相应类型的专属主机的数量；The determination module is also used to determine the number of dedicated hosts of the corresponding type according to the number of virtual machines in the business parameters;
推荐模块，用于向所述用户推荐所述专属主机的类型和数量。A recommendation module is used to recommend the type and quantity of the dedicated hosts to the user.
在一些可能的实现方式中，所述业务参数中的虚拟机数量包括本次需要添加的虚拟机数量。In some possible implementations, the number of virtual machines in the service parameters includes the number of virtual machines that need to be added this time.
在一些可能的实现方式中，所述业务参数中的虚拟机数量还包括虚拟机总数量或负载增加时需要添加的虚拟机数量。In some possible implementations, the number of virtual machines in the service parameters also includes the total number of virtual machines or the number of virtual machines that need to be added when the load increases.
第三方面，本申请提供一种计算设备集群。所述计算设备集群包括至少一台计算设备，所述至少一台计算设备包括至少一个处理器和至少一个存储器。所述至少一个处理器、所述至少一个存储器进行相互的通信。所述至少一个处理器用于执行所述至少一个存储器中存储的指令，以使得计算设备或计算设备集群执行如第一方面或第一方面的任一种实现方式所述的容量管理方法。 In a third aspect, this application provides a computing device cluster. The cluster of computing devices includes at least one computing device including at least one processor and at least one memory. The at least one processor and the at least one memory communicate with each other. The at least one processor is configured to execute instructions stored in the at least one memory, so that the computing device or the computing device cluster executes the capacity management method as described in the first aspect or any implementation of the first aspect.
第四方面，本申请提供一种计算机可读存储介质，所述计算机可读存储介质中存储有指令，所述指令指示计算设备或计算设备集群执行上述第一方面或第一方面的任一种实现方式所述的容量管理方法。In a fourth aspect, the present application provides a computer-readable storage medium in which instructions are stored, and the instructions instruct a computing device or a cluster of computing devices to execute the above-mentioned first aspect or any one of the first aspects. Implement the capacity management method described in the manner.
第五方面，本申请提供了一种包含指令的计算机程序产品，当其在计算设备或计算设备集群上运行时，使得计算设备或计算设备集群执行上述第一方面或第一方面的任一种实现方式所述的容量管理方法。In a fifth aspect, the present application provides a computer program product containing instructions that, when run on a computing device or a cluster of computing devices, cause the computing device or a cluster of computing devices to execute the first aspect or any one of the first aspects. Implement the capacity management method described in the manner.
本申请在上述各方面提供的实现方式的基础上，还可以进行进一步组合以提供更多实现方式。Based on the implementation methods provided in the above aspects, this application can also be further combined to provide more implementation methods.
附图说明Description of the drawings
为了更清楚地说明本申请实施例的技术方法，下面将对实施例中所需使用的附图作以简单地介绍。In order to explain the technical methods of the embodiments of the present application more clearly, the drawings required to be used in the embodiments will be briefly introduced below.
图1为本申请实施例提供的一种容量管理***的架构示意图；Figure 1 is a schematic architectural diagram of a capacity management system provided by an embodiment of the present application;
图2为本申请实施例提供的一种容量管理方法的流程图；Figure 2 is a flow chart of a capacity management method provided by an embodiment of the present application;
图3为本申请实施例提供的一种专属资源池创建界面的界面示意图；Figure 3 is a schematic diagram of an exclusive resource pool creation interface provided by an embodiment of the present application;
图4为本申请实施例提供的一种容量管理界面的界面示意图；Figure 4 is a schematic diagram of a capacity management interface provided by an embodiment of the present application;
图5为本申请实施例提供的一种容量管理***的结构示意图；Figure 5 is a schematic structural diagram of a capacity management system provided by an embodiment of the present application;
图6为本申请实施例提供的一种计算设备的结构示意图；Figure 6 is a schematic structural diagram of a computing device provided by an embodiment of the present application;
图7为本申请实施例提供的一种计算设备集群的结构示意图；Figure 7 is a schematic structural diagram of a computing device cluster provided by an embodiment of the present application;
图8为本申请实施例提供的另一种计算设备集群的结构示意图；Figure 8 is a schematic structural diagram of another computing device cluster provided by an embodiment of the present application;
图9为本申请实施例提供的又一种计算设备集群的结构示意图。Figure 9 is a schematic structural diagram of another computing device cluster provided by an embodiment of the present application.
具体实施方式Detailed ways
本申请实施例中的术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个该特征。The terms "first" and "second" in the embodiments of this application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, features defined as "first" and "second" may explicitly or implicitly include one or more of these features.
首先对本申请实施例中所涉及到的一些技术术语进行介绍。First, some technical terms involved in the embodiments of this application are introduced.
资源池：云计算数据中心中所涉及到的各种硬件和软件的集合。资源池提供的资源可以分为计算资源、存储资源或网络资源。云服务厂商可以将上述资源以云服务的方式提供给用户使用。Resource pool: A collection of various hardware and software involved in cloud computing data centers. The resources provided by the resource pool can be divided into computing resources, storage resources or network resources. Cloud service providers can provide the above resources to users in the form of cloud services.
专属主机(dedicated host，DEH)：是云服务中的一种服务模式，在该服务模式下，用户可以直接购买整个主机而不是虚拟机。其中，虚拟机(virtual machine，VM)，也称作虚拟服务器，是一类基于虚拟化技术在同一台主机/物理服务器(physical machine，PM)上，通过软件模拟的具有完整硬件***功能的、运行在一个完全隔离环境中的完整计算机***。专属主机具有物理资源独享、部署更灵活等特点，不与其他客户共享容量，并且可以控制虚拟机在专属主机上的部署方法。Dedicated host (DEH): It is a service model in cloud services. In this service model, users can directly purchase the entire host instead of a virtual machine. Among them, a virtual machine (VM), also called a virtual server, is a type of computer with complete hardware system functions simulated through software on the same host/physical server (PM) based on virtualization technology. A complete computer system running in a completely isolated environment. Dedicated hosts have the characteristics of exclusive physical resources and more flexible deployment. They do not share capacity with other customers and can control the deployment method of virtual machines on dedicated hosts.
专属资源池：是资源池中用户独享的一部分资源集合，包括计算、网络、存储等多维度资源，同样与其他资源隔离。Exclusive resource pool: It is a collection of resources in the resource pool that are exclusive to users, including multi-dimensional resources such as computing, network, and storage, and are also isolated from other resources.
由于专属资源池具有资源隔离度较高，用户具有绝对控制权等特点，越来越多的用户尝试使用专属资源池作为自己使用云服务时的首选。具体地，用户对属于自己的专属资源池拥有绝对管控的权利。例如，用户可以自由管理专属资源池中专属主机集群上的资源分布，甚至可以指定部署VM的主机，以及指定存储卷和网络的参数。Because dedicated resource pools have the characteristics of high resource isolation and users have absolute control, more and more users try to use dedicated resource pools as their first choice when using cloud services. Specifically, users have absolute control over their own exclusive resource pools. For example, users can freely manage the resource distribution on the dedicated host cluster in the dedicated resource pool, and can even specify the host where the VM is deployed, as well as specify the parameters of the storage volume and network.
然而，用户后续使用专属资源池服务的过程中，云服务厂商提供的资源管理手段比较有限，导致专属资源池的容量管理难以满足业务需求和成本要求。例如，业务规模大幅增长时，云服务厂商难以及时提醒用户购买更多的专属资源，增加专属资源池的容量，满足日益增长的业务需求。又例如，专属资源池中资源长期处于低利用率水平时，云服务厂商并未提醒用户缩减购买的专属资源，以缩小专属资源池的容量，降低成本。However, when users subsequently use dedicated resource pool services, the resource management methods provided by cloud service vendors are relatively limited, making it difficult for the capacity management of dedicated resource pools to meet business needs and cost requirements. For example, when the business scale increases significantly, it is difficult for cloud service providers to promptly remind users to purchase more dedicated resources and increase the capacity of the dedicated resource pool to meet the growing business needs. For another example, when the resources in the dedicated resource pool are at low utilization levels for a long time, the cloud service provider does not remind users to reduce the purchased dedicated resources in order to reduce the capacity of the dedicated resource pool and reduce costs.
有鉴于此，本申请提供一种容量管理方法。该方法可以由云平台侧的容量管理***执行。其中，云平台是云服务厂商基于大量硬件构建的、用于以云服务形式提供计算资源、存储资源、网络资源的平台。为了满足用户的需求，云平台可以向用户提供专属资源池服务。容量管理***用于在用户使用专属资源池服务的过程中，对属于用户的专属资源池进行容量管理(例如是容量伸缩管理)。In view of this, this application provides a capacity management method. This method can be executed by the capacity management system on the cloud platform side. Among them, the cloud platform is a platform built by cloud service vendors based on a large amount of hardware to provide computing resources, storage resources, and network resources in the form of cloud services. In order to meet the needs of users, the cloud platform can provide users with exclusive resource pool services. The capacity management system is used to perform capacity management (for example, capacity scaling management) of the dedicated resource pool belonging to the user when the user uses the dedicated resource pool service.
容量管理***可以是用于对专属资源池进行容量管理的软件***，该软件***可以集成在云平台， 或者是独立使用。容量管理***可以部署在计算设备集群，例如是云计算数据中心的集群，计算设备集群执行软件***的程序代码，从而执行容量管理方法。在一些可能的实现方式中，容量管理***也可以是硬件***，例如是具有容量管理功能的计算设备集群。该硬件***运行时执行本申请的容量管理方法。The capacity management system can be a software system used to manage the capacity of a dedicated resource pool. This software system can be integrated into the cloud platform. Or used independently. The capacity management system can be deployed in a computing device cluster, such as a cluster in a cloud computing data center. The computing device cluster executes the program code of the software system, thereby executing the capacity management method. In some possible implementations, the capacity management system may also be a hardware system, such as a computing device cluster with capacity management functions. When the hardware system is running, the capacity management method of this application is executed.
具体地，容量管理***可以获取专属资源池中至少一个维度的资源使用量，然后根据至少一个维度的资源使用量，确定专属资源池的监测指标项对应的测量值，接着根据上述监测指标项的测量值以及监测指标项对应的告警阈值，确定专属资源池是否满足容量伸缩条件，当专属资源池满足容量伸缩条件时，向用户呈现容量伸缩建议。Specifically, the capacity management system can obtain the resource usage of at least one dimension in the exclusive resource pool, and then determine the measurement value corresponding to the monitoring indicator item of the exclusive resource pool based on the resource usage of at least one dimension, and then determine the measurement value corresponding to the monitoring indicator item of the above-mentioned monitoring indicator item. The measurement values and alarm thresholds corresponding to the monitoring indicator items determine whether the dedicated resource pool meets the capacity scaling conditions. When the dedicated resource pool meets the capacity scaling conditions, capacity scaling recommendations are presented to the user.
该方法通过收集专属资源池中资源使用情况，并在根据资源使用情况确定专属资源池满足容量伸缩条件时向用户呈现容量伸缩建议，从而实现在资源不足导致可发放量减少时提醒用户尽快购买更多专属资源进行扩容，或者在资源使用率长期处于低水平时提醒用户可能容量过剩，可以适当退订部分专属资源进行缩容，如此解决了专属资源池的后续使用过程中因资源规模较大而造成的容量测算困难、容量管理不便的问题。This method collects the resource usage in the dedicated resource pool and presents capacity scaling suggestions to the user when it is determined that the dedicated resource pool meets the capacity scaling conditions based on the resource usage, thereby reminding the user to purchase replacements as soon as possible when insufficient resources lead to a reduction in the amount that can be issued. To expand the capacity of multiple dedicated resources, or to remind users that there may be excess capacity when resource usage is at a low level for a long time, they can appropriately unsubscribe from some dedicated resources to reduce the capacity. This solves the problem of large resource scale in the subsequent use of the dedicated resource pool. This causes problems such as difficulty in capacity measurement and inconvenience in capacity management.
需要说明的是，云服务厂商作为资源提供方，通过收集和分析大量用户在使用专属资源时的资源使用数据，可以实现根据用户输入的业务参数推算出用户在服务周期内所需的专属资源的类型和数量。因此，在用户购买专属资源池服务时，可以允许用户输入业务参数，容量管理***可以指导用户具体购买专属资源如专属主机的类型、数量，以满足用户的业务的各项要求。由此解决用户在购买专属资源池服务时，因知识或经验欠缺导致的购买专属资源数量不合理的问题。It should be noted that cloud service providers, as resource providers, can calculate the dedicated resources required by users within the service cycle based on the business parameters input by users by collecting and analyzing the resource usage data of a large number of users when using exclusive resources. Type and quantity. Therefore, when users purchase dedicated resource pool services, users can be allowed to enter business parameters, and the capacity management system can guide users to specifically purchase dedicated resources such as the type and quantity of dedicated hosts to meet the user's business requirements. This solves the problem of users purchasing an unreasonable number of exclusive resources due to lack of knowledge or experience when purchasing exclusive resource pool services.
为了使得本申请的技术方案更加清楚、易于理解，下面结合附图对本申请的容量管理***的***架构进行说明。In order to make the technical solution of the present application clearer and easier to understand, the system architecture of the capacity management system of the present application will be described below with reference to the accompanying drawings.
参见图1所示的容量管理***的架构示意图，该容量管理***10包括容量管理装置100，容量管理装置100用于在用户使用专属资源池服务的过程中对属于用户的专属资源池进行容量管理。其中，用户在购买专属资源池服务时，可以根据自身的知识或经验配置需要购买的专属资源的类型、数量。进一步地，容量管理***10还可以包括容量推荐装置200，该容量推荐装置200用于在购买专属资源池服务时，向用户推荐专属资源的类型、数量。Referring to the schematic architectural diagram of the capacity management system shown in Figure 1, the capacity management system 10 includes a capacity management device 100. The capacity management device 100 is used to perform capacity management on the dedicated resource pool belonging to the user when the user uses the dedicated resource pool service. . Among them, when users purchase exclusive resource pool services, they can configure the type and quantity of exclusive resources they need to purchase based on their own knowledge or experience. Further, the capacity management system 10 may also include a capacity recommendation device 200, which is used to recommend the type and quantity of dedicated resources to the user when purchasing a dedicated resource pool service.
其中，容量推荐装置100负责接收用户输入的业务参数，包括但不限于业务类型、核数，然后将根据该业务参数为用户推荐需要购买的专属资源的类型和数量，从而满足用户需求。当用户购买包括相应类型和数量的专属资源的专属资源池后，容量管理装置300可以负责帮助用户对购买上述专属资源形成的专属资源池进行资源管理。例如，容量管理装置300可以对专属资源池的剩余资源能够发放的虚拟机数量进行测算(该过程也称作容量测算)，从而在容量不足时进行告警。又例如，容量管理装置200也可以根据用户设置的指标来判断专属资源池是否处于低负载运行的状态，并在低负载时建议用户对专属资源池进行缩容。Among them, the capacity recommendation device 100 is responsible for receiving service parameters input by the user, including but not limited to service type and core number, and then recommends the type and quantity of exclusive resources to be purchased to the user based on the service parameters, thereby meeting the user's needs. After the user purchases a dedicated resource pool that includes dedicated resources of a corresponding type and quantity, the capacity management device 300 may be responsible for helping the user perform resource management on the dedicated resource pool formed by purchasing the above dedicated resources. For example, the capacity management device 300 can calculate the number of virtual machines that can be allocated by the remaining resources of the dedicated resource pool (this process is also called capacity calculation), so as to issue an alarm when the capacity is insufficient. For another example, the capacity management device 200 can also determine whether the dedicated resource pool is in a low-load operation state based on indicators set by the user, and suggest the user to reduce the capacity of the dedicated resource pool when the load is low.
具体地，容量推荐装置100用于接收专属资源池创建请求，该专属资源池创建请求中包括用户输入的业务参数，然后根据所述业务参数中的业务类型和用于实现业务的虚拟机的规格，确定专属主机的类型，接着根据业务参数中的虚拟机数量，确定相应类型的专属主机的数量，向用户推荐专属主机的类型和数量。Specifically, the capacity recommendation device 100 is configured to receive a dedicated resource pool creation request, which includes service parameters input by the user, and then determines the capacity recommendation device 100 according to the service type in the service parameters and the specifications of the virtual machine used to implement the service. , determine the type of dedicated host, and then determine the number of dedicated hosts of the corresponding type based on the number of virtual machines in the business parameters, and recommend the type and number of dedicated hosts to the user.
用户可以根据容量推荐装置100推荐的专属主机的类型和数量购买专属资源池服务，也可以根据自身的经验或知识购买专属资源池服务，获得属于该用户的专属资源池。相应地，容量管理装置200用于获取所述专属资源池中至少一个维度的资源使用量，根据至少一个维度的资源使用量，确定专属资源池的监测指标项对应的测量值，然后根据监测指标项的测量值以及监测指标项对应的告警阈值，确定专属资源池是否满足容量伸缩条件，当专属资源池满足该容量伸缩条件时，向用户呈现容量伸缩建议，从而实现向用户告警，使得用户能够及时对专属资源池进行容量伸缩(扩容或缩容)。Users can purchase dedicated resource pool services based on the type and quantity of dedicated hosts recommended by the capacity recommendation device 100, or purchase dedicated resource pool services based on their own experience or knowledge to obtain a dedicated resource pool belonging to the user. Correspondingly, the capacity management device 200 is configured to obtain the resource usage of at least one dimension in the dedicated resource pool, determine the measurement value corresponding to the monitoring indicator item of the dedicated resource pool based on the resource usage of at least one dimension, and then determine the measurement value according to the monitoring indicator. The measurement value of the item and the alarm threshold corresponding to the monitoring indicator item determine whether the dedicated resource pool meets the capacity scaling conditions. When the dedicated resource pool meets the capacity scaling conditions, capacity scaling suggestions are presented to the user, thereby achieving alarms to the user, so that the user can Capacity scaling (expanding or shrinking) of the dedicated resource pool is performed in a timely manner.
下面对容量推荐装置100和容量管理装置200的功能和具体实现进行详细说明。The functions and specific implementation of the capacity recommendation device 100 and the capacity management device 200 will be described in detail below.
容量推荐装置100主要负责接收用户在创建专属资源池时输入专属资源池创建请求，专属资源池创建请求是和业务相关的请求，专属资源池创建请求中携带有用户输入的业务参数，该业务参数包括本次 需要添加的虚拟机数量。在一些示例中，业务参数还包括业务类型、用户使用的虚拟机的规格。其中，业务类型表征使用专属资源池特性计划实现的功能，例如业务类型可以为Redis、Nginx。虚拟机的规格是指虚拟机的型号，例如虚拟机的规格可以包括16U32G或c7.8xlarge.2。可选地，业务参数还可以包括预估的虚拟机总数量，用户为应用创建的本次所需虚拟机数量，或者后续在应用使用的全生命周期中，由于负载增加时，用户可能为此应用新创建的虚拟机数量。其中，用户未输入预估的虚拟机总数量时，也可以根据历史上同类服务的虚拟机总数量估算。The capacity recommendation device 100 is mainly responsible for receiving a dedicated resource pool creation request input by the user when creating a dedicated resource pool. The dedicated resource pool creation request is a request related to the business. The dedicated resource pool creation request carries business parameters input by the user. The business parameters Including this time The number of virtual machines to be added. In some examples, the service parameters also include the service type and the specifications of the virtual machine used by the user. Among them, the business type represents the functions planned to be implemented using the dedicated resource pool feature. For example, the business type can be Redis or Nginx. The specifications of the virtual machine refer to the model of the virtual machine. For example, the specifications of the virtual machine can include 16U32G or c7.8xlarge.2. Optionally, the business parameters can also include the estimated total number of virtual machines, the number of virtual machines that the user creates for the application this time, or the subsequent number of virtual machines that the user may need due to increased load during the entire life cycle of the application. Apply the number of newly created virtual machines. If the user does not enter the estimated total number of virtual machines, it can also be estimated based on the historical total number of virtual machines of similar services.
当用户输入了以上和业务相关的业务参数后，容量推荐装置100便可以估算出用户需要购买的专属资源的类型和数量。估算用户需要购买的专属资源的类型和数量可以参见如下公式：
After the user inputs the above service parameters related to the service, the capacity recommendation device 100 can estimate the type and quantity of the dedicated resources that the user needs to purchase. To estimate the type and quantity of exclusive resources that users need to purchase, please refer to the following formula:
其中，Demandj为用户输入的本次需要添加的虚拟机在资源j上的总量，例如5台4U8G VM的Demandj便是40。Futurej为用户输入的未来预计会使用到的虚拟机在资源j上的总量。βj为Futurej的修正系数。i为用户指定了业务类型(记作Business)以及虚拟机的规格(记作VM_type)后，通过以往数据经验为用户选择的专属资源(如专属主机)的类型。f(Business，VM_type)为选择专属主机类型的专家的经验选择。例如，对于一些常用应用，如Redis,Nginx,MySQL等，将会根据经验选择一些主机容量较大，中央处理器(central processing unit，CPU)主频较高，内存多通道的专属资源；对于一些通信较多的应用，则会优先选择CPU密度高，通信带宽较大的专属资源。Resourcei,j为类型为i的专属资源在资源维度j上的数量，例如一台包括48个虚拟中央处理器(virtual CPU，vCPU)的主机在CPU维度上的值就是48。αi为最终计算的专属资源数量的修正系数。Among them, Demand j is the total amount of virtual machines that need to be added on resource j input by the user. For example, Demand j for five 4U8G VMs is 40. Future j is the total amount of virtual machines on resource j that is expected to be used in the future input by the user. β j is the correction coefficient of Future j . After i specifies the business type (denoted as Business) and the specifications of the virtual machine (denoted as VM_type) for the user, the type of dedicated resource (such as a dedicated host) is selected for the user based on past data experience. f(Business, VM_type) is the experience choice of experts who choose dedicated host types. For example, for some common applications, such as Redis, Nginx, MySQL, etc., some dedicated resources with larger host capacity, higher central processing unit (CPU) frequency, and multi-channel memory will be selected based on experience; for some Applications with a lot of communication will give priority to dedicated resources with high CPU density and large communication bandwidth. Resource i,j is the number of dedicated resources of type i in resource dimension j. For example, the value of a host including 48 virtual central processing units (virtual CPUs, vCPUs) in the CPU dimension is 48. α i is the correction coefficient of the final calculated number of dedicated resources.
上述公式的计算逻辑为：用户输入本次需要购买的各资源类型总量和未来预期量，例如需要多少核，多少内存等，其中，未来预期量需经过系数修正，一般为0.7-0.9。容量推荐装置100首先根据用户输入的业务类型和虚拟机的规格，据专家经验选择出专属资源的类型。之后在资源的各个维度计算需要的专属资源数量，最后在所有维度资源中选择所需专属资源数量最大维度所需的数量为专属资源数量，将专属资源如专属主机的类型和数量经修正系数修正后推荐给用户，修正系数一般可以设置为1.05-1.2。The calculation logic of the above formula is: the user enters the total amount of each resource type that needs to be purchased this time and the expected future amount, such as how many cores, how much memory, etc. are needed. Among them, the expected future amount needs to be corrected by a coefficient, which is generally 0.7-0.9. The capacity recommendation device 100 first selects the type of dedicated resources based on the service type input by the user and the specifications of the virtual machine, and based on expert experience. Then calculate the required number of dedicated resources in each dimension of the resource. Finally, select the number of required dedicated resources among all dimensional resources. The number required by the largest dimension is the number of dedicated resources. The type and quantity of dedicated resources such as dedicated hosts are corrected by the correction coefficient. After recommending it to users, the correction coefficient can generally be set to 1.05-1.2.
容量管理装置200负责在用户购买了专属资源池后，可以输入自己关注的专属资源集群的指标，用来告知容量管理装置100如何进行资源管理。用户输入的指标可以包括虚拟机列表，该虚拟机列表记录有用户关注的至少一个虚拟机。当监控到专属资源池中剩余资源能够发放上述规格的虚拟机数量(可发放数量)变化或不足时，容量管理装置100可以进行预警。The capacity management device 200 is responsible for inputting the indicators of the dedicated resource clusters that the user is interested in after purchasing the dedicated resource pool to inform the capacity management device 100 how to perform resource management. The indicators input by the user may include a virtual machine list, and the virtual machine list records at least one virtual machine that the user is concerned about. When it is monitored that the number of virtual machines (number that can be allocated) with the above specifications that can be allocated by the remaining resources in the dedicated resource pool changes or is insufficient, the capacity management device 100 can issue an early warning.
进一步地，用户输入的指标还可以包括监控指标项对应的告警阈值。例如，监控指标项包括用户关注的虚拟机的可发放数量时，用户输入的指标还可以包括上述虚拟机的可发放数量的告警阈值，也称作虚拟机的剩余量阈值、第一告警阈值。当用户关注的虚拟机的可发放数量低于上述虚拟机的剩余量阈值时，容量管理装置100可以向用户发送告警。Further, the indicators input by the user may also include alarm thresholds corresponding to the monitoring indicator items. For example, when the monitoring indicator item includes the issuable number of the virtual machines that the user is concerned about, the indicators input by the user may also include the alarm threshold for the issuable number of the virtual machines, which is also called the remaining virtual machine threshold and the first alarm threshold. When the issuance quantity of the virtual machine that the user is concerned about is lower than the remaining quantity threshold of the virtual machine, the capacity management device 100 may send an alarm to the user.
类似地，用户输入的指标还可以包括用户关注的虚拟机的发放比例，例如为关注的VM比例。具体地，用户可以输入自己的专属资源池中，期望的能发放的VM数量可理解为最小单元。例如，用户某个需求需要8个8xlarge.2,5个4xlarge.2,10个2xlarge.2虚拟机来执行自己的业务，则用户可以输入上述虚拟机的型号(VM规格)和数量。Similarly, the indicators input by the user may also include the proportion of virtual machines that the user is concerned about, such as the proportion of VMs that the user is concerned about. Specifically, users can enter their own dedicated resource pool, and the expected number of VMs that can be issued can be understood as the minimum unit. For example, if a user needs 8 8xlarge.2, 5 4xlarge.2, or 10 2xlarge.2 virtual machines to execute their business, the user can enter the model (VM specification) and quantity of the above virtual machines.
容量管理装置100可以对用户输入的虚拟机列表和发放比例进行容量测算，对用户关心的监控指标项进行实时监控，并且在容量不足时对用户进行扩容预警；在专属资源池的资源使用率较低时对用户建议缩容。The capacity management device 100 can calculate the capacity of the virtual machine list and allocation ratio input by the user, perform real-time monitoring of the monitoring indicator items that the user is concerned about, and provide an expansion warning to the user when the capacity is insufficient; when the resource usage rate of the dedicated resource pool is relatively high, When it is low, users are advised to scale down.
容量测算的基本方法为：用户首先输入自己希望知道的VM类型和发放比例，之后会根据当前专属资源池内的资源使用情况，计算出用户关心的VM的可发放数量。测算公式如下：


The basic method of capacity calculation is: the user first inputs the VM type and issuance ratio that he wants to know, and then the number of VMs that the user cares about is calculated based on the resource usage in the current dedicated resource pool. The calculation formula is as follows:


其中，ai,j为用户购买的专属资源i的第j维的剩余资源量(可以由购买的资源总量和资源使用量确定)。αk代表用户输入的、虚拟机列表中不同虚拟机的发放比例。例如输入[8 8xlarge.2,5 4xlarge.2,10 2xlarge.2],则αk的值便是8,5,10。rk,j代表用户输入的、虚拟机列表中不同虚拟机第j维资源的数量，在上述例子中,rk,j的在vCPU维度的值便是32,16,8。bj为用户输入的、该用户关注的虚拟机列表中j维资源的总和。Si为用户的专属资源i中可以按照用户输入的发放比例发放的VM数量。S′i,k为专属资源i按比例发放完用户输入的虚拟机列表中的所有虚拟机在某一维的资源总和后，剩余资源量仍可发放的第k个虚拟机数。Among them, a i,j is the remaining resource amount in the jth dimension of the exclusive resource i purchased by the user (which can be determined by the total amount of purchased resources and resource usage). αk represents the provisioning ratio of different virtual machines in the virtual machine list input by the user. For example, if you input [8 8xlarge.2,5 4xlarge.2,10 2xlarge.2], the value of α k is 8,5,10. r k,j represents the number of jth-dimensional resources of different virtual machines in the virtual machine list input by the user. In the above example, the value of r k,j in the vCPU dimension is 32,16,8. b j is the sum of j-dimensional resources in the virtual machine list that the user is interested in input by the user. S i is the number of VMs that can be issued in the user's exclusive resource i according to the issuance ratio input by the user. S′ i,k is the number of k-th virtual machines that can still be allocated the remaining resources after the dedicated resource i is allocated proportionally to the total resources of all virtual machines in the virtual machine list entered by the user in a certain dimension.
其计算逻辑如下：容量管理装置100根据用户输入的、自己关注的虚拟机列表，包括VM数量和VM规格，计算出列表内VM所需的各维度资源量。之后在每个专属资源中，计算能够发放的VM数量。对于资源发放后的剩余空间，可逐个计算列表内每个VM的可发放数量，之后累计得到可发放数量。The calculation logic is as follows: the capacity management device 100 calculates the amount of resources in each dimension required by the VMs in the list based on the list of virtual machines that the user inputs and is of interest to, including the number of VMs and VM specifications. Then, in each dedicated resource, calculate the number of VMs that can be issued. For the remaining space after resource allocation, the allocable quantity of each VM in the list can be calculated one by one, and then the allocable quantity can be accumulated.
容量管理装置100的一个功能是针对专属资源池提供伸缩建议(扩容预警或缩容建议)。用户可以通过设置预警触发的标准来控制预警的产生。通常用户的输入是他关心的一系列VM的可发放数量降低到某个值之后，比如用户可以指定当集群的8xlarge.2规格的VM可发放数量小于5，且4xlarge.2规格的VM可发放数量小于10时触发预警。具体的VM可发放数量可以由容量测算的结果得出。One function of the capacity management device 100 is to provide scaling recommendations (capacity expansion warnings or capacity reduction recommendations) for a dedicated resource pool. Users can control the generation of early warnings by setting the criteria for warning triggering. Usually the user's input is after the number of VMs he cares about is reduced to a certain value. For example, the user can specify that when the number of VMs of the 8xlarge.2 specification in the cluster that can be issued is less than 5, and the number of VMs of the 4xlarge.2 specification can be issued. An early warning is triggered when the number is less than 10. The specific number of VMs that can be issued can be obtained from the results of capacity calculation.
缩容建议的使用方法与扩容类似，目的是当集群内资源使用率持续处在一个较低的状态时，帮助用户减少资源的使用量。具体地，用户可以配置：当集群中某项资源的资源使用率持续一个窗口期低于某个阈值时，对用户进行缩容建议。例如，用户可以配置集群中vCPU的资源使用率持续3个小时低于30％时，便可以进行缩容建议。其中，集群中资源使用率的计算方法为：
The recommended usage method of scaling down is similar to scaling up. The purpose is to help users reduce resource usage when the resource usage in the cluster continues to be in a low state. Specifically, users can configure: when the resource usage of a certain resource in the cluster continues to be lower than a certain threshold for a window period, scaling down recommendations will be made to the user. For example, users can configure scaling recommendations when the vCPU resource usage in the cluster continues to be lower than 30% for 3 hours. Among them, the calculation method of resource usage in the cluster is:
其中，ηj为资源维度j的使用率，bk,j为用户购买的VMk的第j维资源使用数量，ai,j为用户购买的专属资源i的第j维资源总量。Among them, η j is the usage rate of resource dimension j, b k, j is the j-th dimension resource usage quantity of VM k purchased by the user, and a i, j is the total amount of j-th dimension resource of exclusive resource i purchased by the user.
本申请通过构建了一套在专属资源池服务中，在用户创建专属资源池时通过容量推荐装置200的容量计算公式，将用户输入的业务参数转化为推荐用户购买的专属资源(如专属主机)的类型和数量，为用户创建专属资源池提供指导。之后在用户使用专属资源池的过程中，还提供了一套容量管理装置100帮助用户管理专属资源池的容量。该容量管理装置100可以帮助用户进行容量预警或缩容建议，减少用户管理集群容量的不便，改善用户体验。This application constructs a set of capacity calculation formulas through the capacity recommendation device 200 when the user creates an exclusive resource pool in the exclusive resource pool service, and converts the business parameters input by the user into exclusive resources (such as exclusive hosts) that the user is recommended to purchase. The type and quantity provide guidance for users to create exclusive resource pools. Later, when the user uses the dedicated resource pool, a set of capacity management device 100 is also provided to help the user manage the capacity of the dedicated resource pool. The capacity management device 100 can help users make capacity warnings or reduce capacity recommendations, reduce users' inconvenience in cluster capacity management, and improve user experience.
基于图1所示的容量管理***10，本申请实施例还提供一种容量管理方法，下面结合附图对本申请实施例的容量管理方法进行介绍。Based on the capacity management system 10 shown in Figure 1, an embodiment of the present application also provides a capacity management method. The capacity management method of the embodiment of the present application is introduced below with reference to the accompanying drawings.
参见图2所示的容量管理方法的流程图，该方法包括：Referring to the flow chart of the capacity management method shown in Figure 2, the method includes:
S202：容量推荐装置200接收资源池创建请求。S202: The capacity recommendation device 200 receives a resource pool creation request.
专属资源池创建请求中包括用户输入的业务参数。业务参数具体是与用户业务相关的参数，包括但不限于业务类型、用于实现业务的虚拟机的规格、虚拟机数量。其中，虚拟机是将资源封装实现隔离的基本单元，虚拟机可以通过虚拟化技术实现。虚拟机数量可以包括本次需要添加的虚拟机数量。The dedicated resource pool creation request includes the business parameters entered by the user. Service parameters are specifically parameters related to user services, including but not limited to service type, specifications of virtual machines used to implement services, and the number of virtual machines. Among them, the virtual machine is the basic unit that encapsulates resources to achieve isolation. The virtual machine can be implemented through virtualization technology. The number of virtual machines can include the number of virtual machines that need to be added this time.
可选地，虚拟机数量还可以包括虚拟机总数量或负载增加时需要添加的虚拟机数量。后续在应用使用的全生命周期中，由于负载增加，用户可能为此应用新创建虚拟机，因此，用户可以配置负载增加时需要添加的虚拟机数量。其中，用户未输入虚拟机总数量等业务参数时，容量推荐装置200可以参考历史上同类服务的相关指标。Optionally, the number of virtual machines can also include the total number of virtual machines or the number of virtual machines that need to be added when the load increases. Later, during the entire life cycle of the application, due to the increase in load, users may create new virtual machines for this application. Therefore, users can configure the number of virtual machines that need to be added when the load increases. When the user does not input service parameters such as the total number of virtual machines, the capacity recommendation device 200 may refer to relevant indicators of similar services in history.
为了便于理解，下面结合一具体示例进行说明。In order to facilitate understanding, the following is explained with a specific example.
参见图3所示的专属资源池创建界面的示意图，专属资源池创建界面300包括业务参数配置组件302和提交组件304。其中，业务参数配置组件302包括本次需要添加VM数量配置控件3022和VM总量配置控件3024、用户为应用创建的本次所需VM数量配置控件3026、后续为应用新增VM数量配置控件3028，用户可以通过上述配置控件分别配置本次需要添加的VM数量、预估的VM总量(也即VM总数量)、用户为应用创建的本次所需VM数量、后续在应用使用的全生命周期中，由于负载增加时， 用户可能为此应用新创建的VM数量。需要说明的是，VM总量是可选项，当用户未配置时，容量推荐装置200可以获取历史上同类服务的相关参数。提交组件304包括提交控件3042和取消控件3044，当用户触发提交控件3042时，可以提交用户配置的上述业务参数，当用户触发取消控件3044时，可以取消配置。Referring to the schematic diagram of the dedicated resource pool creation interface shown in Figure 3, the dedicated resource pool creation interface 300 includes a business parameter configuration component 302 and a submission component 304. Among them, the business parameter configuration component 302 includes the configuration control for the number of VMs that need to be added this time 3022 and the total number of VMs configuration control 3024, the configuration control for the number of VMs needed this time created by the user for the application 3026, and the subsequent configuration control for the number of new VMs for the application 3028 , the user can use the above configuration controls to separately configure the number of VMs to be added this time, the estimated total number of VMs (that is, the total number of VMs), the number of VMs required this time created by the user for the application, and the subsequent full life of the application. During the cycle, due to the increase in load, The number of new VMs that the user may create for this application. It should be noted that the total amount of VMs is optional. When the user does not configure it, the capacity recommendation device 200 can obtain relevant parameters of similar services in history. The submission component 304 includes a submission control 3042 and a cancellation control 3044. When the user triggers the submission control 3042, the above business parameters configured by the user can be submitted. When the user triggers the cancellation control 3044, the configuration can be canceled.
S204：容量推荐装置200根据业务参数中的业务类型和用于实现业务的虚拟机的规格，确定专属主机的类型。S204: The capacity recommendation device 200 determines the type of dedicated host based on the service type in the service parameters and the specifications of the virtual machine used to implement the service.
具体地，容量推荐装置200可以根据公式(1)中的i＝f(Business，VM_type)，以及业务参数中的业务类型和用于实现业务的资源隔离单元的规格，确定专属主机的类型。例如，容量推荐装置200可以将业务类型、虚拟机规格，代入上述公式(1)中的i＝f(Business，VM_type)，从而确定专属主机的类型。Specifically, the capacity recommendation device 200 can determine the type of the dedicated host according to i=f (Business, VM_type) in formula (1), as well as the service type in the service parameters and the specifications of the resource isolation unit used to implement the service. For example, the capacity recommendation device 200 can substitute the business type and virtual machine specifications into i=f (Business, VM_type) in the above formula (1) to determine the type of the dedicated host.
其中，f可以根据专家经验选择。对于一些常用应用如Redis,Nginx,MySQL等，将会根据经验选择一些主机容量较大，CPU主频较高，内存多通道的专属主机；对于一些通信较多的应用，则会优先选择CPU密度高，通信带宽较大的专属主机。Among them, f can be selected based on expert experience. For some common applications such as Redis, Nginx, MySQL, etc., some dedicated hosts with larger host capacity, higher CPU frequency, and multi-channel memory will be selected based on experience; for some applications with more communication, CPU density will be given priority. High, dedicated host with large communication bandwidth.
S206：容量推荐装置200根据业务参数中的资源隔离单元的数量，确定相应类型的专属主机的数量。S206: The capacity recommendation device 200 determines the number of dedicated hosts of the corresponding type according to the number of resource isolation units in the service parameters.
具体地，容量推荐装置200可以根据公式(1)中的以及业务参数中的资源隔离单元的数量，确定相应类型的专属主机的数量。例如，容量推荐装置200可以将业务参数中的虚拟机数量，如VM数量代入上述公式(1)中的从而获得相应类型的专属主机的数量。Specifically, the capacity recommendation device 200 can be based on the formula (1) And the number of resource isolation units in the business parameters determines the number of dedicated hosts of the corresponding type. For example, the capacity recommendation device 200 can substitute the number of virtual machines in the service parameters, such as the number of VMs, into the equation (1) above. Thereby obtaining the number of dedicated hosts of the corresponding type.
S208：容量推荐装置200向所述用户推荐所述专属主机的类型和数量。S208: The capacity recommendation device 200 recommends the type and quantity of the dedicated hosts to the user.
具体地，容量推荐装置200可以通过结果展示界面，向用户展示专属主机的类型和数量，从而实现向用户推荐上述类型的专属主机，以及推荐购买的数量，进而指导用户购买合理的专属资源，避免资源浪费或者难以满足要求。Specifically, the capacity recommendation device 200 can display the type and quantity of dedicated hosts to the user through the result display interface, thereby recommending the above types of dedicated hosts to the user, as well as the recommended quantity to purchase, and thereby guiding the user to purchase reasonable dedicated resources to avoid Resources are wasted or it is difficult to meet requirements.
S210：容量管理装置100获取用户购买的专属资源池中至少一个维度的资源使用量。S210: The capacity management device 100 obtains the resource usage of at least one dimension in the exclusive resource pool purchased by the user.
用户可以按照推荐的专属主机的类型和数量，或者参考推荐专属主机的类型和数量，购买专属主机形成专属资源池。相应地，容量管理装置100可以获取用户购买的专属资源池中至少一个维度(例如是各个维度)的资源使用量。其中，维度可以是计算、存储或者网络(带宽)。Users can purchase dedicated hosts to form a dedicated resource pool according to the recommended types and quantities of dedicated hosts, or by referring to the recommended types and quantities of dedicated hosts. Correspondingly, the capacity management device 100 can obtain the resource usage of at least one dimension (for example, each dimension) in the dedicated resource pool purchased by the user. Among them, the dimension can be computing, storage or network (bandwidth).
S211：容量管理装置100根据所述至少一个维度的资源使用量，确定所述专属资源池的监测指标项对应的测量值。S211: The capacity management device 100 determines the measurement value corresponding to the monitoring indicator item of the dedicated resource pool based on the resource usage of the at least one dimension.
在一些可能的实现方式中，容量管理装置100可以根据专属资源池中至少一个维度的资源总量以及至少一个维度的资源使用量，确定所述专属资源池的剩余资源能够发放的虚拟机数量。其中，容量管理装置100可以根据至少一个维度的资源使用量以及购买的至少一个维度的资源总量，确定至少一个维度的剩余资源量，然后根据至少一个维度的剩余资源量以及虚拟机在至少一个维度的资源需求量，确定所述专属资源池的剩余资源能够发放的虚拟机数量。In some possible implementations, the capacity management apparatus 100 may determine the number of virtual machines that can be allocated by the remaining resources of the dedicated resource pool based on the total amount of resources in at least one dimension and the resource usage in at least one dimension in the dedicated resource pool. The capacity management device 100 may determine the remaining resource amount in at least one dimension based on the resource usage in at least one dimension and the total amount of purchased resources in at least one dimension, and then determine the remaining resource amount in at least one dimension based on the remaining resource amount in at least one dimension and the virtual machine in at least one dimension. The resource demand of the dimension determines the number of virtual machines that can be issued from the remaining resources of the dedicated resource pool.
容量管理装置100还可以支持用户配置该用户关注的虚拟机。具体地，容量管理装置100接收用户通过容量管理界面配置的虚拟机列表，该虚拟机列表记录有用户关注的至少一个虚拟机，相应地，容量管理装置100可以根据虚拟机列表中至少一个虚拟机的规格确定至少一个虚拟机在至少一个维度的资源需求量。在获得用户关注的虚拟机在至少一个维度的资源需求量后，容量管理装置100可以根据容量资源池中至少一个维度的资源量和虚拟机在至少一个维度的资源需求量，确定专属资源池的剩余资源能够发放的虚拟机数量。The capacity management device 100 can also support the user in configuring the virtual machines that the user is interested in. Specifically, the capacity management device 100 receives a virtual machine list configured by the user through the capacity management interface. The virtual machine list records at least one virtual machine that the user is concerned about. Correspondingly, the capacity management device 100 can configure the virtual machine according to at least one virtual machine in the virtual machine list. The specifications determine the resource requirements of at least one virtual machine in at least one dimension. After obtaining the resource demand of the virtual machine that the user is paying attention to in at least one dimension, the capacity management device 100 can determine the resource demand of the dedicated resource pool based on the resource amount of at least one dimension in the capacity resource pool and the resource demand of the virtual machine in at least one dimension. The number of virtual machines that can be allocated with remaining resources.
进一步地，不同型号的虚拟机可以按照比例发放，容量管理装置100还支持用户配置该用户关注的多个虚拟机的发放比例，例如容量管理装置100可以接收用户通过容量管理界面配置的多个虚拟机的发放比例。其中，虚拟机的发放比例可以通过各虚拟机的数量表征。换言之，容量管理装置100支持用户通过容量管理界面配置的虚拟机的型号和数量，虚拟机列表中记录虚拟机的型号和数量。为了便于理解，本申请实施例还提供了虚拟机列表的示例：Further, virtual machines of different types can be distributed according to proportions. The capacity management device 100 also supports the user to configure the distribution proportions of multiple virtual machines that the user is concerned about. For example, the capacity management device 100 can receive multiple virtual machines configured by the user through the capacity management interface. The distribution ratio of machines. Among them, the distribution ratio of virtual machines can be characterized by the number of each virtual machine. In other words, the capacity management device 100 supports the model and quantity of virtual machines configured by the user through the capacity management interface, and the model and quantity of the virtual machines are recorded in the virtual machine list. To facilitate understanding, the embodiment of this application also provides an example of a virtual machine list:
表1虚拟机列表
Table 1 Virtual machine list
其中，表1的第一列为虚拟机的型号，表1的第二列为相应型号的虚拟机数量，基于此，型号为8xlarge.2、4xlarge.2、2xlarge.2的虚拟机的发放比例可以为8:5:10。Among them, the first column in Table 1 is the model of the virtual machine, and the second column in Table 1 is the number of virtual machines of the corresponding model. Based on this, the distribution proportion of virtual machines with models 8xlarge.2, 4xlarge.2, and 2xlarge.2 It could be 8:5:10.
基于此，容量管理装置100在确定专属资源池的剩余资源能够发放的虚拟机数量时，还可以结合上述发放比例。具体地，容量管理装置100可以根据专属资源池中至少一个维度的剩余资源量以及多个虚拟机在至少一个维度的资源需求量、多个虚拟机的发放比例，确定按照发放比例发放时专属资源池的剩余资源能够发放的虚拟机数量。Based on this, the capacity management device 100 may also combine the above allocation ratio when determining the number of virtual machines that can be allocated from the remaining resources of the dedicated resource pool. Specifically, the capacity management device 100 can determine the dedicated resources to be distributed according to the distribution ratio based on the remaining resource amount in at least one dimension of the dedicated resource pool, the resource demand of multiple virtual machines in at least one dimension, and the issuance ratio of the multiple virtual machines. The number of virtual machines that can be allocated by the remaining resources of the pool.
其中，容量管理装置100确定专属资源池的剩余资源能够发放的虚拟机数量的过程可以参考上述公式(2)、(3)、(4)，在此不再赘述。The process by which the capacity management device 100 determines the number of virtual machines that can be allocated from the remaining resources of the dedicated resource pool can refer to the above formulas (2), (3), and (4), which will not be described again here.
在另一些可能的实现方式中，容量管理装置100可以根据专属资源池中至少一个维度的资源总量以及至少一个维度的资源使用量，确定所述至少一个维度的资源使用率。参见上述公式(5)，针对任一维度，容量管理装置100可以对各个虚拟机在该维度的资源使用量和购买量分别进行累计，然后确定累计资源使用量与累计资源购买量的比值，从而确定该维度的资源使用率。In other possible implementations, the capacity management apparatus 100 may determine the resource usage rate of at least one dimension based on the total amount of resources in at least one dimension and the resource usage of at least one dimension in the dedicated resource pool. Referring to the above formula (5), for any dimension, the capacity management device 100 can accumulate the resource usage and purchase amount of each virtual machine in that dimension, and then determine the ratio of the cumulative resource usage to the cumulative resource purchase amount, so as to Determine resource usage for this dimension.
S212：容量管理装置100根据监测指标项的测量值以及监测指标项对应的告警阈值，确定专属资源池是否满足容量伸缩条件。当专属资源池满足容量伸缩条件时，执行S214。S212: The capacity management device 100 determines whether the dedicated resource pool meets the capacity expansion condition based on the measured value of the monitoring indicator item and the alarm threshold corresponding to the monitoring indicator item. When the dedicated resource pool meets the capacity scaling conditions, S214 is executed.
容量伸缩条件可以包括扩容条件或缩容条件中的一种。扩容条件或缩容条件可以由用户设置。例如，用户可以通过容量管理界面配置扩容时的监控指标项以及与该监控指标项对应的第一告警阈值，从而设置扩容条件。其中，扩容时的监控指标项可以是专属资源池的剩余资源能够发放的虚拟机数量，例如为用户关注的虚拟机的可发放数量。又例如，用户可以通过容量管理界面配置缩容时的监控指标项以及与该监控指标项对应的第二告警阈值，从而设置缩容条件。其中，缩容时的监控指标项可以为资源使用率，例如是至少一个维度的资源使用率。Capacity scaling conditions may include one of capacity expansion conditions or capacity reduction conditions. The expansion conditions or shrinking conditions can be set by the user. For example, users can configure the monitoring indicator items during capacity expansion and the first alarm threshold corresponding to the monitoring indicator items through the capacity management interface, thereby setting expansion conditions. Among them, the monitoring indicator item during capacity expansion may be the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool, for example, the number of virtual machines that can be issued that the user is concerned about. For another example, the user can configure the monitoring indicator item during capacity reduction and the second alarm threshold corresponding to the monitoring indicator item through the capacity management interface, thereby setting the reduction conditions. The monitoring indicator item during scaling down may be resource usage, for example, resource usage in at least one dimension.
容量管理装置100可以将专属资源池的剩余资源能够发放的虚拟机数量与第一告警阈值进行比较，当专属资源池的剩余资源能够发放的虚拟机数量小于第一告警阈值，则表明专属资源池满足容量伸缩条件中的扩容条件。The capacity management device 100 can compare the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool with the first alarm threshold. When the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool is less than the first alarm threshold, it indicates that the dedicated resource pool Meet the expansion conditions in the capacity expansion conditions.
类似地，容量管理装置100可以将至少一个维度的资源使用率与至少一个维度的资源使用率对应的第二告警阈值进行比较，从而确定专属资源池是否满足容量伸缩条件。例如，至少一个维度的资源使用率在一个时间窗口持续小于第二告警阈值，则表明专属资源池满足容量伸缩条件中的缩容条件。Similarly, the capacity management device 100 may compare the resource usage in at least one dimension with the second alarm threshold corresponding to the resource usage in at least one dimension, thereby determining whether the dedicated resource pool meets the capacity scaling condition. For example, if the resource usage of at least one dimension continues to be less than the second alarm threshold in a time window, it indicates that the dedicated resource pool meets the scaling conditions in the capacity scaling conditions.
为了便于理解，下面结合一具体示例进行说明。In order to facilitate understanding, the following is explained with a specific example.
参见图4所示的容量管理界面400的示意图，容量管理界面400包括扩容监控配置组件402、缩容监控配置组件404和提交组件406，其中，扩容监控配置组件402、缩容监控配置组件404分别包括相应的监控指标配置控件和阈值配置控件，具体为扩容监控指标配置控件4022、扩容告警阈值配置控件4024、缩容监控指标配置控件4042、缩容告警阈值配置控件4044。其中，扩容监控配置组件402中还可以包括关注列表配置控件4026、关注比例配置控件4028。当用户通过上述配置控件完成监控指标项、告警阈值以及虚拟机列表(虚拟机及其发放比例)的配置，可以通过提交组件406中的提交控件4062完成提交。需要说明，用户也可以通过提交组件406中的取消控件4064取消提交。Referring to the schematic diagram of the capacity management interface 400 shown in Figure 4, the capacity management interface 400 includes a capacity expansion monitoring configuration component 402, a capacity reduction monitoring configuration component 404, and a submission component 406. The capacity expansion monitoring configuration component 402 and the capacity reduction monitoring configuration component 404 are respectively It includes the corresponding monitoring indicator configuration control and threshold configuration control, specifically the expansion monitoring indicator configuration control 4022, the expansion alarm threshold configuration control 4024, the reduction monitoring indicator configuration control 4042, and the reduction alarm threshold configuration control 4044. Among them, the expansion monitoring configuration component 402 may also include a focus list configuration control 4026 and a focus ratio configuration control 4028. When the user completes the configuration of monitoring indicator items, alarm thresholds, and virtual machine lists (virtual machines and their provisioning proportions) through the above configuration controls, the submission can be completed through the submission control 4062 in the submission component 406. It should be noted that the user can also cancel the submission through the cancellation control 4064 in the submission component 406.
S214：容量管理装置100向用户呈现容量伸缩建议。S214: The capacity management device 100 presents capacity expansion and contraction suggestions to the user.
伸缩建议包括提醒用户扩容或缩容的建议。伸缩建议还可以包括扩容量或缩容量。其中，扩容量可以根据专属资源池的剩余资源能够发放的虚拟机数量和第一告警阈值确定。缩容量可以根据资源使用率与第二告警阈值确定。Scaling recommendations include suggestions to remind users to expand or shrink capacity. Scaling recommendations can also include increasing or decreasing capacity. The capacity expansion can be determined based on the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool and the first alarm threshold. The amount of shrinkage can be determined based on resource usage and the second alarm threshold.
上述S202至S208为本申请实施例的可选步骤，执行本申请实施例的容量管理方法也可以不执行上述S202至S208。例如，用户也可以根据自身经验，自行决策需要购买的专属主机的类型和数量。The above-mentioned S202 to S208 are optional steps in the embodiment of the present application, and the above-mentioned S202 to S208 may not be executed when performing the capacity management method in the embodiment of the present application. For example, users can also decide on their own the type and quantity of dedicated hosts they need to purchase based on their own experience.
基于上述内容描述，本申请实施例提供的容量管理方法可以在用户购买了专属资源池服务后，使用容量管理装置100帮助用户进行容量管理，包括可发放数量测算以及提供容量伸缩建议等，使用户在使用时知晓可发放数量信息，并且允许用户设置容量不足的第一告警阈值，或是在资源使用量达不到相应 的第二告警阈值时进行缩容建议。Based on the above description, the capacity management method provided by the embodiment of the present application can use the capacity management device 100 to help the user perform capacity management after the user purchases a dedicated resource pool service, including calculating the issuable quantity and providing capacity scaling suggestions, etc., so that the user can Know the amount information that can be issued when using it, and allow users to set the first alarm threshold for insufficient capacity, or when the resource usage does not reach the corresponding When the second alarm threshold is reached, scaling down is recommended.
此外，该方法还支持用户在购买专属资源池时，输入业务参数，如此可以通过容量推荐装置200帮助用户在此次服务中可能需要购买的资源量进行测算，在满足用户使用需求的情况下，能够指导用户合理购买，避免资源浪费，节约用户成本。且对比无指导的专属资源购买方式能够大大改善用户体验。In addition, this method also supports users to input business parameters when purchasing an exclusive resource pool, so that the capacity recommendation device 200 can help the user calculate the amount of resources that may need to be purchased in this service. Under the condition that the user's usage needs are met, It can guide users to make reasonable purchases, avoid resource waste, and save user costs. And compared with the unguided exclusive resource purchase method, the user experience can be greatly improved.
为了本申请的技术方案更加清楚、易于理解，下面结合一场景进行说明。该场景包括购买阶段和使用阶段的容量管理。In order to make the technical solution of the present application clearer and easier to understand, it will be described below in conjunction with a scenario. This scenario includes capacity management in the purchase phase and usage phase.
购买阶段：用户在购买专属资源时，可以与容量推荐装置200进行交互。首先用户输入业务参数，例如业务类型、用于实现业务的虚拟机的规格、虚拟机数量等。容量推荐装置200接收到用户输入的业务参数，在后台测算出用户需要购买的专属资源的类型和每种专属资源的数量。其中，容量推荐装置200根据经验或专家规则，以及虚拟机到专属资源的转换公式计算用户需要使用的专属资源的类型和数量(资源量)，之后会将推荐值反馈给用户。例如用户输入自己的业务为Redis，且需要总核数为500核32U的VM，容量推荐装置200可以测算出用户可能需要10台某种规格的专属主机。用户可以根据推荐结果来进行专属资源购买决策。Purchase stage: When purchasing exclusive resources, the user can interact with the capacity recommendation device 200 . First, the user inputs service parameters, such as service type, specifications of virtual machines used to implement the service, number of virtual machines, etc. The capacity recommendation device 200 receives the service parameters input by the user and calculates the type of exclusive resources that the user needs to purchase and the quantity of each exclusive resource in the background. Among them, the capacity recommendation device 200 calculates the type and quantity (amount of resources) of dedicated resources that the user needs to use based on experience or expert rules and the conversion formula from virtual machines to dedicated resources, and then feeds back the recommended values to the user. For example, the user inputs that his business is Redis and requires a VM with a total core count of 500 cores and 32U. The capacity recommendation device 200 can calculate that the user may need 10 dedicated hosts of a certain specification. Users can make exclusive resource purchase decisions based on the recommendation results.
使用阶段：当用户购买了专属资源池之后，可以使用到容量管理装置100。在容量管理界面除了够看到集群的基础资源状态(如各维度的资源使用量和剩余资源量)，还可以设置自己关注的虚拟机及其发放比例，并根据此比例对虚拟机的可发放数量进行测算。测算的结果为剩余的专属资源可以继续按照此比例发放多少VM。容量管理装置100还可以允许用户在容量管理界面设置不同告警阈值，例如集群可发放的4xlarge.2VM的值低于10时，告知用户进行扩容。缩容建议功能同理，用户可以设置缩容建议的触发条件，例如当集群的vCPU使用率连续24个小时都低于30％时，提供缩容建议。Usage stage: After the user purchases a dedicated resource pool, the capacity management device 100 can be used. In the capacity management interface, in addition to seeing the basic resource status of the cluster (such as resource usage and remaining resources in each dimension), you can also set the virtual machines you care about and their issuance proportions, and adjust the provisioning ratio of the virtual machines based on this proportion. Calculate the quantity. The result of the calculation is how many VMs can be allocated based on the remaining dedicated resources according to this ratio. The capacity management device 100 can also allow the user to set different alarm thresholds on the capacity management interface. For example, when the value of 4xlarge.2VM that can be issued by the cluster is lower than 10, the user is notified to expand the capacity. The same applies to the shrink recommendation function. Users can set trigger conditions for shrink recommendations. For example, when the vCPU usage of the cluster is lower than 30% for 24 consecutive hours, shrink recommendations will be provided.
本申请还提供一种容量管理***10，容量管理***10部署在云平台侧，云平台向用户提供专属资源池服务，该容器管理***10用于在用户使用所述专属资源池服务的过程中对属于用户的专属资源池进行容量管理。如图5所示，容量管理***10包括容量管理装置100，该容量管理装置100包括：This application also provides a capacity management system 10. The capacity management system 10 is deployed on the cloud platform side. The cloud platform provides exclusive resource pool services to users. The container management system 10 is used in the process of users using the exclusive resource pool services. Capacity management of user-specific resource pools. As shown in Figure 5, the capacity management system 10 includes a capacity management device 100. The capacity management device 100 includes:
获取模块101，用于获取所述专属资源池中至少一个维度的资源使用量；The acquisition module 101 is used to obtain the resource usage of at least one dimension in the exclusive resource pool;
监测模块103，用于根据所述至少一个维度的资源使用量，确定所述专属资源池的监测指标项对应的测量值；The monitoring module 103 is configured to determine the measurement value corresponding to the monitoring indicator item of the exclusive resource pool based on the resource usage of the at least one dimension;
告警模块105，用于根据所述监测指标项的测量值以及所述监测指标项对应的告警阈值，确定所述专属资源池是否满足容量伸缩条件，当所述专属资源池满足所述容量伸缩条件时，向所述用户呈现容量伸缩建议。The alarm module 105 is configured to determine whether the dedicated resource pool meets the capacity scaling condition based on the measured value of the monitoring indicator item and the alarm threshold corresponding to the monitoring indicator item. When the dedicated resource pool meets the capacity scaling condition , the user is presented with capacity scaling suggestions.
示例性地，上述容量管理装置100可以通过硬件实现，或者可以通过软件实现。For example, the above-mentioned capacity management device 100 can be implemented by hardware, or can be implemented by software.
当通过软件实现时，容量管理装置100可以是运行在计算设备上的应用程序，如计算引擎等。该应用程序可以以虚拟化服务的方式提供给用户使用。虚拟化服务可以包括虚拟机VM服务、裸金属服务器(bare metal server，BMS)服务以及容器(container)服务。其中，VM服务可以是通过虚拟化技术在多个物理主机(如计算设备)上虚拟出虚拟机资源池以为用户按需提供VM进行使用的服务。BMS服务是在多个物理主机上虚拟出BMS资源池以为用户按需提供BMS进行使用的服务。容器服务是在多个物理主机上虚拟出容器资源池以为用户按需提供容器进行使用的服务。VM是模拟出来的一台虚拟的计算机，也即逻辑上的一台计算机。BMS是一种可弹性伸缩的高性能计算服务，计算性能与传统物理机无差别，具有安全物理隔离的特点。容器是一种内核虚拟化技术，可以提供轻量级的虚拟化，以达到隔离用户空间、进程和资源的目的。应理解，上述虚拟化服务中的VM服务、BMS服务以及容器服务仅仅是作为具体的示例，在实际应用中，虚拟化服务还可以是其他轻量级或者重量级的虚拟化服务，此处不作具体限定。When implemented by software, the capacity management device 100 may be an application program running on a computing device, such as a computing engine. The application can be provided to users as a virtualized service. Virtualization services can include virtual machine VM services, bare metal server (bare metal server, BMS) services, and container (container) services. Among them, the VM service can be a service that uses virtualization technology to virtualize a virtual machine resource pool on multiple physical hosts (such as computing devices) to provide users with VMs for use on demand. The BMS service is a service that virtualizes BMS resource pools on multiple physical hosts to provide users with BMS on demand. Container service is a service that virtualizes container resource pools on multiple physical hosts to provide users with containers on demand. VM is a simulated virtual computer, that is, a logical computer. BMS is an elastically scalable high-performance computing service. Its computing performance is the same as that of traditional physical machines, and it has the characteristics of safe physical isolation. Containers are a kernel virtualization technology that can provide lightweight virtualization to isolate user space, processes and resources. It should be understood that the VM service, BMS service and container service in the above virtualization services are only specific examples. In actual applications, the virtualization service can also be other lightweight or heavyweight virtualization services, which are not discussed here. Specific limitations.
当通过硬件实现时，容量管理装置100中可以包括至少一个计算设备，如服务器等。或者，容量管理装置100也可以是利用专用集成电路(application-specific integrated circuit，ASIC)实现、或可编程逻辑器件(programmable logic device，PLD)实现的设备等。其中，上述PLD可以是复杂程序逻辑器件(complex programmable logical device，CPLD)、现场可编程门阵列(field-programmable gate array，FPGA)、通用 阵列逻辑(generic array logic，GAL)或其任意组合实现。When implemented by hardware, the capacity management device 100 may include at least one computing device, such as a server. Alternatively, the capacity management device 100 may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). Among them, the above-mentioned PLD can be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a general-purpose Array logic (generic array logic, GAL) or any combination thereof.
进一步地，容量管理装置100中的获取模块101、监测模块103或告警模块105也可以通过软件或者硬件实现。Furthermore, the acquisition module 101, the monitoring module 103 or the alarm module 105 in the capacity management device 100 can also be implemented by software or hardware.
当通过软件实现时，获取模块101、监测模块103或告警模块105可以是运行在计算设备上的应用程序，如计算引擎等。当通过硬件实现时，获取模块101、监测模块103或告警模块105可以包括至少一个计算设备，如服务器等。或者，获取模块101、监测模块103或告警模块105也可以是利用专用集成电路ASIC实现、或可编程逻辑器件PLD实现的设备等。When implemented by software, the acquisition module 101, the monitoring module 103 or the alarm module 105 may be an application program running on a computing device, such as a computing engine. When implemented by hardware, the acquisition module 101, the monitoring module 103 or the alarm module 105 may include at least one computing device, such as a server. Alternatively, the acquisition module 101, the monitoring module 103 or the alarm module 105 can also be a device implemented using an application specific integrated circuit (ASIC) or a programmable logic device (PLD).
在一些可能的实现方式中，所述监测指标项包括所述专属资源池的剩余资源能够发放的虚拟机数量或资源使用率中的一种或多种。In some possible implementations, the monitoring indicator items include one or more of the number of virtual machines that can be allocated by the remaining resources of the dedicated resource pool or the resource usage rate.
在一些可能的实现方式中，所述监控指标项所述包括专属资源池的剩余资源能够发放的虚拟机数量；In some possible implementations, the monitoring indicator item includes the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool;
所述监测模块103具体用于：The monitoring module 103 is specifically used for:
根据所述专属资源池中至少一个维度的资源总量以及所述至少一个维度的资源使用量，确定所述专属资源池中至少一个维度的剩余资源量；Determine the remaining resource amount of at least one dimension in the exclusive resource pool according to the total amount of resources in at least one dimension in the exclusive resource pool and the resource usage in the at least one dimension;
根据所述专属资源池中至少一个维度的剩余资源量以及虚拟机在至少一个维度的资源需求量，确定所述专属资源池的剩余资源能够发放的虚拟机数量。The number of virtual machines that can be issued by the remaining resources of the dedicated resource pool is determined based on the amount of remaining resources in at least one dimension of the dedicated resource pool and the resource demand of the virtual machines in at least one dimension.
在一些可能的实现方式中，所述装置100还包括：In some possible implementations, the device 100 further includes:
配置模块107，用于接收所述用户通过容量管理界面配置的虚拟机列表，所述虚拟机列表记录有所述用户关注的至少一个虚拟机；Configuration module 107, configured to receive a virtual machine list configured by the user through the capacity management interface, where the virtual machine list records at least one virtual machine that the user is concerned about;
所述监测模块103还用于：The monitoring module 103 is also used to:
根据所述虚拟机列表中所述至少一个虚拟机的规格确定所述至少一个虚拟机在至少一个维度的资源需求量。Determine the resource requirement of the at least one virtual machine in at least one dimension according to the specifications of the at least one virtual machine in the virtual machine list.
在一些可能的实现方式中，所述虚拟机列表记录有所述用户关注的多个虚拟机；In some possible implementations, the virtual machine list records multiple virtual machines that the user is interested in;
所述配置模块107还用于：The configuration module 107 is also used to:
接收所述用户通过所述容量管理界面配置的所述多个虚拟机的发放比例；Receive the issuance ratio of the multiple virtual machines configured by the user through the capacity management interface;
所述监测模块103具体用于：The monitoring module 103 is specifically used for:
根据所述专属资源池中至少一个维度的剩余资源量以及所述多个虚拟机在至少一个维度的资源需求量、所述多个虚拟机的发放比例，确定按照所述发放比例发放时所述专属资源池的剩余资源能够发放的虚拟机数量。According to the remaining resource amount in at least one dimension of the dedicated resource pool, the resource demand of the multiple virtual machines in at least one dimension, and the issuance ratio of the multiple virtual machines, determine the amount of resources when issuing according to the issuance ratio. The number of virtual machines that can be allocated from the remaining resources of the dedicated resource pool.
在一些可能的实现方式中，所述监控指标项所述包括资源使用率；In some possible implementations, the monitoring indicator items include resource usage;
所述监测模块103具体用于：The monitoring module 103 is specifically used for:
根据所述专属资源池中至少一个维度的资源总量以及所述至少一个维度的资源使用量，确定所述至少一个维度的资源使用率。The resource usage rate of the at least one dimension is determined based on the total amount of resources of at least one dimension in the dedicated resource pool and the resource usage of the at least one dimension.
在一些可能的实现方式中，所述***10还包括容量推荐装置200，所述容量推荐装置200包括：In some possible implementations, the system 10 further includes a capacity recommendation device 200. The capacity recommendation device 200 includes:
通信模块201，用于接收专属资源池创建请求，所述专属资源池创建请求中包括用户输入的业务参数；The communication module 201 is configured to receive a dedicated resource pool creation request, where the dedicated resource pool creation request includes business parameters input by the user;
确定模块203，用于根据所述业务参数中的业务类型和用于实现业务的虚拟机的规格，确定专属主机的类型；The determination module 203 is used to determine the type of the dedicated host according to the service type in the service parameters and the specifications of the virtual machine used to implement the service;
所述确定模块203，还用于根据所述业务参数中的虚拟机数量，确定相应类型的专属主机的数量；The determination module 203 is also used to determine the number of dedicated hosts of the corresponding type according to the number of virtual machines in the business parameters;
推荐模块205，用于向所述用户推荐所述专属主机的类型和数量。The recommendation module 205 is used to recommend the type and quantity of the dedicated hosts to the user.
在一些可能的实现方式中，所述业务参数中的虚拟机数量包括本次需要添加的虚拟机数量。In some possible implementations, the number of virtual machines in the service parameters includes the number of virtual machines that need to be added this time.
在一些可能的实现方式中，所述业务参数中的虚拟机数量还包括虚拟机总数量或负载增加时需要添加的虚拟机数量。In some possible implementations, the number of virtual machines in the service parameters also includes the total number of virtual machines or the number of virtual machines that need to be added when the load increases.
本申请还提供一种计算设备600。如图6所示，计算设备600包括：总线602、处理器604、存储器606和通信接口608。处理器604、存储器606和通信接口608之间通过总线602通信。计算设备600可以是服务器或终端设备。应理解，本申请不限定计算设备600中的处理器、存储器的个数。The present application also provides a computing device 600. As shown in Figure 6, computing device 600 includes: bus 602, processor 604, memory 606, and communication interface 608. The processor 604, the memory 606 and the communication interface 608 communicate through the bus 602. Computing device 600 may be a server or a terminal device. It should be understood that this application does not limit the number of processors and memories in the computing device 600.
总线602可以是外设部件互连标准(peripheral component interconnect，PCI)总线或扩展工业标准结 构(extended industry standard architecture，EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。为便于表示，图6中仅用一条线表示，但并不表示仅有一根总线或一种类型的总线。总线602可包括在计算设备600各个部件(例如，存储器606、处理器604、通信接口608)之间传送信息的通路。Bus 602 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture. (extended industry standard architecture, EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of presentation, only one line is used in Figure 6, but it does not mean that there is only one bus or one type of bus. Bus 602 may include a path that carries information between various components of computing device 600 (eg, memory 606, processor 604, communications interface 608).
处理器604可以包括中央处理器(central processing unit，CPU)、图形处理器(graphics processing unit，GPU)、微处理器(micro processor，MP)或者数字信号处理器(digital signal processor，DSP)等处理器中的任意一种或多种。The processor 604 may include a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP) or a digital signal processor (DSP). any one or more of them.
存储器606可以包括易失性存储器(volatile memory)，例如随机存取存储器(random access memory，RAM)。存储器606还可以包括非易失性存储器(non-volatile memory)，例如只读存储器(read-only memory，ROM)，快闪存储器，机械硬盘(hard disk drive，HDD)或固态硬盘(solid state drive，SSD)。存储器606中存储有可执行的程序代码，处理器604执行该可执行的程序代码以实现前述容量管理方法。具体的，存储器606上存有容量管理***10用于执行容量管理方法的指令。Memory 606 may include volatile memory, such as random access memory (RAM). Memory 606 may also include non-volatile memory (non-volatile memory), such as read-only memory (ROM), flash memory, mechanical hard disk (hard disk drive, HDD) or solid state drive (solid state drive) ,SSD). The memory 606 stores executable program code, and the processor 604 executes the executable program code to implement the aforementioned capacity management method. Specifically, the memory 606 stores instructions for the capacity management system 10 to execute the capacity management method.
通信接口608使用例如但不限于网络接口卡、收发器一类的收发模块，来实现计算设备600与其他设备或通信网络之间的通信。The communication interface 608 uses transceiver modules such as, but not limited to, network interface cards and transceivers to implement communication between the computing device 600 and other devices or communication networks.
本申请实施例还提供了一种计算设备集群。该计算设备集群包括至少一台计算设备。该计算设备可以是服务器，例如是中心服务器、边缘服务器，或者是本地数据中心中的本地服务器。在一些实施例中，计算设备也可以是台式机、笔记本电脑或者智能手机等终端设备。An embodiment of the present application also provides a computing device cluster. The computing device cluster includes at least one computing device. The computing device may be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device may also be a terminal device such as a desktop computer, a laptop computer, or a smartphone.
如图7所示，所述计算设备集群包括至少一个计算设备600。计算设备集群中的一个或多个计算设备600中的存储器606中可以存有相同的容量管理***10用于执行容量管理方法的指令。As shown in FIG. 7 , the computing device cluster includes at least one computing device 600 . Instructions for the same capacity management system 10 to perform the capacity management method may be stored in the memory 606 of one or more computing devices 600 in the cluster of computing devices.
在一些可能的实现方式中，该计算设备集群中的一个或多个计算设备600也可以用于执行容量管理***10用于执行容量管理方法的部分指令。换言之，一个或多个计算设备600的组合可以共同执行容量管理***10用于执行容量管理方法的指令。In some possible implementations, one or more computing devices 600 in the computing device cluster may also be used to execute part of the instructions of the capacity management system 10 for executing the capacity management method. In other words, a combination of one or more computing devices 600 may collectively execute instructions of the capacity management system 10 for performing the capacity management method.
需要说明的是，计算设备集群中的不同的计算设备600中的存储器606可以存储不同的指令，用于执行容量管理***10的部分功能。It should be noted that the memory 606 in different computing devices 600 in the computing device cluster may store different instructions for executing part of the functions of the capacity management system 10 .
图8示出了一种可能的实现方式。如图8所示，两个计算设备600A和600B通过通信接口608实现连接。计算设备600A中的存储器上存有用于执行容量管理装置100的功能的指令。计算设备600B中的存储器上存有用于执行容量管理装置100的功能的指令。换言之，计算设备600A和600B的存储器606共同存储了容量管理***10用于执行容量管理方法的指令。Figure 8 shows a possible implementation. As shown in FIG. 8 , two computing devices 600A and 600B are connected through a communication interface 608 . Stored on memory in computing device 600A are instructions for performing the functions of capacity management device 100 . Stored on memory in computing device 600B are instructions for performing the functions of capacity management device 100 . In other words, memory 606 of computing devices 600A and 600B collectively stores instructions for capacity management system 10 to perform the capacity management method.
图8所示的计算设备集群之间的连接方式可以是考虑到本申请提供的容量管理方法需要大量计算推算出用户需要购买的专属主机的类型和数量。因此，考虑将容量推荐装置200实现的功能交由计算设备600B执行。The connection method between computing device clusters shown in Figure 8 can be based on the fact that the capacity management method provided by this application requires a large amount of calculations to deduce the type and quantity of dedicated hosts that the user needs to purchase. Therefore, it is considered that the functions implemented by the capacity recommendation device 200 are performed by the computing device 600B.
应理解，图8中示出的计算设备600A的功能也可以由多个计算设备600完成。同样，计算设备600B的功能也可以由多个计算设备600完成。It should be understood that the functions of the computing device 600A shown in FIG. 8 may also be performed by multiple computing devices 600. Likewise, the functions of computing device 600B may also be performed by multiple computing devices 600 .
在一些可能的实现方式中，计算设备集群中的一个或多个计算设备可以通过网络连接。其中，所述网络可以是广域网或局域网等等。图9示出了一种可能的实现方式。如图9所示，两个计算设备600C和600D之间通过网络进行连接。具体地，通过各个计算设备中的通信接口与所述网络进行连接。在这一类可能的实现方式中，计算设备600C中的存储器606中存有执行容量管理装置100的功能的指令。同时，计算设备600D中的存储器606中存有执行容量推荐装置200的功能的指令。In some possible implementations, one or more computing devices in a cluster of computing devices may be connected through a network. Wherein, the network may be a wide area network or a local area network, etc. Figure 9 shows a possible implementation. As shown in Figure 9, two computing devices 600C and 600D are connected through a network. Specifically, the connection to the network is made through a communication interface in each computing device. In this type of possible implementation, the memory 606 in the computing device 600C stores instructions for performing the functions of the capacity management device 100 . At the same time, instructions for performing the functions of the capacity recommendation device 200 are stored in the memory 606 of the computing device 600D.
图9所示的计算设备集群之间的连接方式可以是考虑到本申请提供的容量管理方法需要大量计算推算出用户需要购买的专属主机的类型和数量，因此考虑将容量推荐装置200实现的功能交由计算设备600D执行。The connection method between computing device clusters shown in Figure 9 can be: Considering that the capacity management method provided by this application requires a large amount of calculations to deduce the type and number of dedicated hosts that the user needs to purchase, the functions implemented by the capacity recommendation device 200 are considered handed over to the computing device 600D for execution.
应理解，图9中示出的计算设备600C的功能也可以由多个计算设备600完成。同样，计算设备600D的功能也可以由多个计算设备600完成。It should be understood that the functions of the computing device 600C shown in FIG. 9 may also be performed by multiple computing devices 600. Likewise, the functions of computing device 600D may also be performed by multiple computing devices 600.
本申请实施例还提供了一种计算机可读存储介质。所述计算机可读存储介质可以是计算设备能够存储的任何可用介质或者是包含一个或多个可用介质的数据中心等数据存储设备。所述可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质(例如固态硬盘)等。 该计算机可读存储介质包括指令，所述指令指示计算设备执行上述应用于容量管理***10用于执行容量管理方法。An embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium may be any available medium that a computing device can store or a data storage device such as a data center that contains one or more available media. The usable media may be magnetic media (eg, floppy disk, hard disk, tape), optical media (eg, DVD), or semiconductor media (eg, solid state drive), etc. The computer-readable storage medium includes instructions that instruct the computing device to execute the above-described application to the capacity management system 10 for performing the capacity management method.
本申请实施例还提供了一种包含指令的计算机程序产品。所述计算机程序产品可以是包含指令的，能够运行在计算设备上或被储存在任何可用介质中的软件或程序产品。当所述计算机程序产品在至少一个计算设备上运行时，使得至少一个计算设备执行上述容量管理方法。An embodiment of the present application also provides a computer program product containing instructions. The computer program product may be a software or program product containing instructions capable of running on a computing device or stored in any available medium. When the computer program product is run on at least one computing device, at least one computing device is caused to execute the above capacity management method.
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的保护范围。 Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that it can still be used Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent substitutions are made to some of the technical features; however, these modifications or substitutions do not cause the essence of the corresponding technical solutions to depart from the protection scope of the technical solutions of the various embodiments of the present invention.

Claims (21)

  1. 一种容量管理方法，其特征在于，由云平台侧的容量管理***执行，所述云平台向用户提供专属资源池服务，所述容器管理***用于在所述用户使用所述专属资源池服务的过程中对属于所述用户的专属资源池进行容量管理，所述方法包括：A capacity management method, characterized in that it is executed by a capacity management system on the cloud platform side. The cloud platform provides exclusive resource pool services to users, and the container management system is used to use the exclusive resource pool services when the users use the dedicated resource pool services. In the process of capacity management of the exclusive resource pool belonging to the user, the method includes:
    获取所述专属资源池中至少一个维度的资源使用量；Obtain the resource usage of at least one dimension in the exclusive resource pool;
    根据所述至少一个维度的资源使用量，确定所述专属资源池的监测指标项对应的测量值；Determine the measurement value corresponding to the monitoring indicator item of the exclusive resource pool according to the resource usage of the at least one dimension;
    根据所述监测指标项的测量值以及所述监测指标项对应的告警阈值，确定所述专属资源池是否满足容量伸缩条件；Determine whether the dedicated resource pool meets the capacity scaling condition based on the measured value of the monitoring indicator item and the alarm threshold corresponding to the monitoring indicator item;
    当所述专属资源池满足所述容量伸缩条件时，向所述用户呈现容量伸缩建议。When the dedicated resource pool meets the capacity scaling condition, a capacity scaling suggestion is presented to the user.
  2. 根据权利要求1所述的方法，其特征在于，所述监测指标项包括所述专属资源池的剩余资源能够发放的虚拟机数量或资源使用率中的一种或多种。The method according to claim 1, wherein the monitoring indicator item includes one or more of the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool or the resource usage rate.
  3. 根据权利要求1或2所述的方法，其特征在于，所述监控指标项所述包括专属资源池的剩余资源能够发放的虚拟机数量；The method according to claim 1 or 2, characterized in that the monitoring indicator item includes the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool;
    所述根据所述至少一个维度的资源使用量，确定所述专属资源池的监测指标项对应的测量值，包括：Determining the measurement value corresponding to the monitoring indicator item of the exclusive resource pool based on the resource usage of the at least one dimension includes:
    根据所述专属资源池中至少一个维度的资源总量以及所述至少一个维度的资源使用量，确定所述专属资源池中至少一个维度的剩余资源量；Determine the remaining resource amount of at least one dimension in the exclusive resource pool according to the total amount of resources in at least one dimension in the exclusive resource pool and the resource usage in the at least one dimension;
    根据所述专属资源池中至少一个维度的剩余资源量以及虚拟机在至少一个维度的资源需求量，确定所述专属资源池的剩余资源能够发放的虚拟机数量。The number of virtual machines that can be issued by the remaining resources of the dedicated resource pool is determined based on the amount of remaining resources in at least one dimension of the dedicated resource pool and the resource demand of the virtual machines in at least one dimension.
  4. 根据权利要求3所述的方法，其特征在于，所述方法还包括：The method of claim 3, further comprising:
    接收所述用户通过容量管理界面配置的虚拟机列表，所述虚拟机列表记录有所述用户关注的至少一个虚拟机；Receive a virtual machine list configured by the user through the capacity management interface, where the virtual machine list records at least one virtual machine that the user is interested in;
    根据所述虚拟机列表中所述至少一个虚拟机的规格确定所述至少一个虚拟机在至少一个维度的资源需求量。Determine the resource requirement of the at least one virtual machine in at least one dimension according to the specifications of the at least one virtual machine in the virtual machine list.
  5. 根据权利要求4所述的方法，其特征在于，所述虚拟机列表记录有所述用户关注的多个虚拟机；The method according to claim 4, wherein the virtual machine list records multiple virtual machines that the user is concerned about;
    所述方法还包括：The method also includes:
    接收所述用户通过所述容量管理界面配置的所述多个虚拟机的发放比例；Receive the issuance ratio of the multiple virtual machines configured by the user through the capacity management interface;
    所述根据所述专属资源池中至少一个维度的剩余资源量以及虚拟机在至少一个维度的资源需求量，确定所述专属资源池的剩余资源能够发放的虚拟机数量，包括：Determining the number of virtual machines that can be issued by the remaining resources of the exclusive resource pool based on the amount of remaining resources in at least one dimension of the exclusive resource pool and the resource demand of the virtual machines in at least one dimension includes:
    根据所述专属资源池中至少一个维度的剩余资源量以及所述多个虚拟机在至少一个维度的资源需求量、所述多个虚拟机的发放比例，确定按照所述发放比例发放时所述专属资源池的剩余资源能够发放的虚拟机数量。According to the remaining resource amount in at least one dimension of the dedicated resource pool, the resource demand of the multiple virtual machines in at least one dimension, and the issuance ratio of the multiple virtual machines, determine the amount of resources when issuing according to the issuance ratio. The number of virtual machines that can be allocated from the remaining resources of the dedicated resource pool.
  6. 根据权利要求1或2所述的方法，其特征在于，所述监控指标项所述包括资源使用率；The method according to claim 1 or 2, characterized in that the monitoring indicator items include resource usage;
    所述根据所述至少一个维度的资源使用量，确定所述专属资源池的监测指标项对应的测量值，包括：Determining the measurement value corresponding to the monitoring indicator item of the exclusive resource pool based on the resource usage of the at least one dimension includes:
    根据所述专属资源池中至少一个维度的资源总量以及所述至少一个维度的资源使用量，确定所述至少一个维度的资源使用率。The resource usage rate of the at least one dimension is determined based on the total amount of resources of at least one dimension in the dedicated resource pool and the resource usage of the at least one dimension.
  7. 根据权利要求1至6任一项所述的方法，其特征在于，所述方法还包括：The method according to any one of claims 1 to 6, characterized in that the method further includes:
    接收专属资源池创建请求，所述专属资源池创建请求中包括用户输入的业务参数；Receive an exclusive resource pool creation request, where the exclusive resource pool creation request includes business parameters input by the user;
    根据所述业务参数中的业务类型和用于实现业务的虚拟机的规格，确定专属主机的类型；Determine the type of dedicated host according to the service type in the service parameters and the specifications of the virtual machine used to implement the service;
    根据所述业务参数中的虚拟机数量，确定相应类型的专属主机的数量；Determine the number of dedicated hosts of the corresponding type according to the number of virtual machines in the business parameters;
    向所述用户推荐所述专属主机的类型和数量。Recommend the type and quantity of the dedicated hosts to the user.
  8. 根据权利要求7所述的方法，其特征在于，所述业务参数中的虚拟机数量包括本次需要添加的虚拟机数量。The method according to claim 7, characterized in that the number of virtual machines in the service parameters includes the number of virtual machines that need to be added this time.
  9. 根据权利要求8所述的方法，其特征在于，所述业务参数中的虚拟机数量还包括虚拟机总数量或负载增加时需要添加的虚拟机数量。The method according to claim 8, characterized in that the number of virtual machines in the service parameters also includes the total number of virtual machines or the number of virtual machines that need to be added when the load increases.
  10. 一种容量管理***，其特征在于，所述容量管理***部署在云平台侧，所述云平台向用户提供专属资源池服务，所述容器管理***用于在所述用户使用所述专属资源池服务的过程中对属于所述用户 的专属资源池进行容量管理，所述容量管理***包括容量管理装置，所述容量管理装置包括：A capacity management system, characterized in that the capacity management system is deployed on the cloud platform side, the cloud platform provides exclusive resource pool services to users, and the container management system is used to use the exclusive resource pool when the user During the service process, the users who belong to the A dedicated resource pool is used for capacity management. The capacity management system includes a capacity management device. The capacity management device includes:
    获取模块，用于获取所述专属资源池中至少一个维度的资源使用量；An acquisition module, used to acquire the resource usage of at least one dimension in the exclusive resource pool;
    监测模块，用于根据所述至少一个维度的资源使用量，确定所述专属资源池的监测指标项对应的测量值；A monitoring module, configured to determine the measurement value corresponding to the monitoring indicator item of the exclusive resource pool based on the resource usage of the at least one dimension;
    告警模块，用于根据所述监测指标项的测量值以及所述监测指标项对应的告警阈值，确定所述专属资源池是否满足容量伸缩条件，当所述专属资源池满足所述容量伸缩条件时，向所述用户呈现容量伸缩建议。An alarm module, configured to determine whether the dedicated resource pool meets the capacity scaling condition based on the measured value of the monitoring indicator item and the alarm threshold corresponding to the monitoring indicator item. When the dedicated resource pool meets the capacity scaling condition, , presenting capacity scaling suggestions to the user.
  11. 根据权利要求10所述的***，其特征在于，所述监测指标项包括所述专属资源池的剩余资源能够发放的虚拟机数量或资源使用率中的一种或多种。The system according to claim 10, wherein the monitoring indicator item includes one or more of the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool or the resource usage rate.
  12. 根据权利要求10或11所述的***，其特征在于，所述监控指标项所述包括专属资源池的剩余资源能够发放的虚拟机数量；The system according to claim 10 or 11, wherein the monitoring indicator item includes the number of virtual machines that can be issued by the remaining resources of the dedicated resource pool;
    所述监测模块具体用于：The monitoring module is specifically used for:
    根据所述专属资源池中至少一个维度的资源总量以及所述至少一个维度的资源使用量，确定所述专属资源池中至少一个维度的剩余资源量；Determine the remaining resource amount of at least one dimension in the exclusive resource pool according to the total amount of resources in at least one dimension in the exclusive resource pool and the resource usage in the at least one dimension;
    根据所述专属资源池中至少一个维度的剩余资源量以及虚拟机在至少一个维度的资源需求量，确定所述专属资源池的剩余资源能够发放的虚拟机数量。The number of virtual machines that can be issued by the remaining resources of the dedicated resource pool is determined based on the amount of remaining resources in at least one dimension of the dedicated resource pool and the resource demand of the virtual machines in at least one dimension.
  13. 根据权利要求12所述的***，其特征在于，所述容量管理装置还包括：The system according to claim 12, characterized in that the capacity management device further includes:
    配置模块，用于接收所述用户通过容量管理界面配置的虚拟机列表，所述虚拟机列表记录有所述用户关注的至少一个虚拟机；A configuration module configured to receive a virtual machine list configured by the user through the capacity management interface, where the virtual machine list records at least one virtual machine that the user is concerned about;
    所述监测模块还用于：The monitoring module is also used to:
    根据所述虚拟机列表中所述至少一个虚拟机的规格确定所述至少一个虚拟机在至少一个维度的资源需求量。Determine the resource requirement of the at least one virtual machine in at least one dimension according to the specifications of the at least one virtual machine in the virtual machine list.
  14. 根据权利要求13所述的***，其特征在于，所述虚拟机列表记录有所述用户关注的多个虚拟机；The system according to claim 13, wherein the virtual machine list records multiple virtual machines that the user is concerned about;
    所述配置模块还用于：The configuration module is also used to:
    接收所述用户通过所述容量管理界面配置的所述多个虚拟机的发放比例；Receive the issuance ratio of the multiple virtual machines configured by the user through the capacity management interface;
    所述监测模块具体用于：The monitoring module is specifically used for:
    根据所述专属资源池中至少一个维度的剩余资源量以及所述多个虚拟机在至少一个维度的资源需求量、所述多个虚拟机的发放比例，确定按照所述发放比例发放时所述专属资源池的剩余资源能够发放的虚拟机数量。According to the remaining resource amount in at least one dimension of the dedicated resource pool, the resource demand of the multiple virtual machines in at least one dimension, and the issuance ratio of the multiple virtual machines, determine the amount of resources when issuing according to the issuance ratio. The number of virtual machines that can be allocated from the remaining resources of the dedicated resource pool.
  15. 根据权利要求10或11所述的***，其特征在于，所述监控指标项所述包括资源使用率；The system according to claim 10 or 11, characterized in that the monitoring indicator items include resource usage;
    所述监测模块具体用于：The monitoring module is specifically used for:
    根据所述专属资源池中至少一个维度的资源总量以及所述至少一个维度的资源使用量，确定所述至少一个维度的资源使用率。The resource usage rate of the at least one dimension is determined based on the total amount of resources of at least one dimension in the dedicated resource pool and the resource usage of the at least one dimension.
  16. 根据权利要求10至15任一项所述的***，其特征在于，所述***还包括容量推荐装置，所述容量推荐装置包括：The system according to any one of claims 10 to 15, characterized in that the system further includes a capacity recommendation device, and the capacity recommendation device includes:
    通信模块，用于接收专属资源池创建请求，所述专属资源池创建请求中包括用户输入的业务参数；A communication module, configured to receive a dedicated resource pool creation request, where the dedicated resource pool creation request includes business parameters input by the user;
    确定模块，用于根据所述业务参数中的业务类型和用于实现业务的虚拟机的规格，确定专属主机的类型；A determination module configured to determine the type of the dedicated host based on the service type in the service parameters and the specifications of the virtual machine used to implement the service;
    所述确定模块，还用于根据所述业务参数中的虚拟机数量，确定相应类型的专属主机的数量；The determination module is also used to determine the number of dedicated hosts of the corresponding type according to the number of virtual machines in the business parameters;
    推荐模块，用于向所述用户推荐所述专属主机的类型和数量。A recommendation module is used to recommend the type and quantity of the dedicated hosts to the user.
  17. 根据权利要求16所述的***，其特征在于，所述业务参数中的虚拟机数量包括本次需要添加的虚拟机数量。The system according to claim 16, characterized in that the number of virtual machines in the business parameters includes the number of virtual machines that need to be added this time.
  18. 根据权利要求17所述的***，其特征在于，所述业务参数中的虚拟机数量还包括虚拟机总数量或负载增加时需要添加的虚拟机数量。The system according to claim 17, wherein the number of virtual machines in the service parameters also includes the total number of virtual machines or the number of virtual machines that need to be added when the load increases.
  19. 一种计算设备集群，其特征在于，所述计算设备集群包括至少一台计算设备，所述至少一台计算设备包括至少一个处理器和至少一个存储器，所述至少一个存储器中存储有计算机可读指令；所述至 少一个处理器执行所述计算机可读指令，以使得所述计算设备集群执行如权利要求1至9中任一项所述的方法。A computing device cluster, characterized in that the computing device cluster includes at least one computing device, the at least one computing device includes at least one processor and at least one memory, and the at least one memory stores computer-readable instruction; instructions to At least one processor executes the computer readable instructions, so that the cluster of computing devices performs the method of any one of claims 1 to 9.
  20. 一种计算机可读存储介质，其特征在于，包括计算机可读指令；所述计算机可读指令用于实现权利要求1至9任一项所述的方法。A computer-readable storage medium, characterized by comprising computer-readable instructions; the computer-readable instructions are used to implement the method described in any one of claims 1 to 9.
  21. 一种计算机程序产品，其特征在于，包括计算机可读指令；所述计算机可读指令用于实现权利要求1至9任一项所述的方法。 A computer program product, characterized by comprising computer readable instructions; the computer readable instructions are used to implement the method described in any one of claims 1 to 9.
PCT/CN2023/101337 2022-09-07 2023-06-20 Capacity management method and related system WO2024051267A1 (en)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN202211091597 2022-09-07
CN202211091597.6 2022-09-07
CN202310064017.2 2023-01-16
CN202310064017.2A CN117707687A (en) 2022-09-07 2023-01-16 Capacity management method and related system

Publications (1)

Publication Number Publication Date
WO2024051267A1 true WO2024051267A1 (en) 2024-03-14

Family

ID=90150323

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/101337 WO2024051267A1 (en) 2022-09-07 2023-06-20 Capacity management method and related system

Country Status (2)

Country Link
CN (1) CN117707687A (en)
WO (1) WO2024051267A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130111468A1 (en) * 2011-10-27 2013-05-02 Verizon Patent And Licensing Inc. Virtual machine allocation in a computing on-demand system
CN110308985A (en) * 2019-05-17 2019-10-08 平安科技（深圳）有限公司 The exclusive server resource management method, apparatus of cloud, equipment and storage medium
CN111796908A (en) * 2020-06-18 2020-10-20 聚好看科技股份有限公司 System and method for automatic elastic expansion and contraction of resources and cloud platform
CN112019577A (en) * 2019-05-29 2020-12-01 ***通信集团重庆有限公司 Exclusive cloud storage implementation method and device, computing equipment and computer storage medium
CN113760543A (en) * 2021-08-09 2021-12-07 万翼科技有限公司 Resource management method and device, electronic equipment and computer readable storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130111468A1 (en) * 2011-10-27 2013-05-02 Verizon Patent And Licensing Inc. Virtual machine allocation in a computing on-demand system
CN110308985A (en) * 2019-05-17 2019-10-08 平安科技（深圳）有限公司 The exclusive server resource management method, apparatus of cloud, equipment and storage medium
CN112019577A (en) * 2019-05-29 2020-12-01 ***通信集团重庆有限公司 Exclusive cloud storage implementation method and device, computing equipment and computer storage medium
CN111796908A (en) * 2020-06-18 2020-10-20 聚好看科技股份有限公司 System and method for automatic elastic expansion and contraction of resources and cloud platform
CN113760543A (en) * 2021-08-09 2021-12-07 万翼科技有限公司 Resource management method and device, electronic equipment and computer readable storage medium

Also Published As

Publication number Publication date
CN117707687A (en) 2024-03-15

Similar Documents

Publication Publication Date Title
US11593179B2 (en) Capacity and load analysis using storage attributes
US10348582B1 (en) Providing an instance availability estimate
JP7189997B2 (en) Rolling resource credits for scheduling virtual computer resources
US10120727B2 (en) Techniques to allocate configurable computing resources
US11455183B2 (en) Adjusting virtual machine migration plans based on alert conditions related to future migrations
US10691647B2 (en) Distributed file system metering and hardware resource usage
US10261819B2 (en) Determining an optimal computing environment for running an image based on performance of similar images
US10592280B2 (en) Resource allocation and scheduling for batch jobs
US8799897B2 (en) Automated cost calculation for virtualized infrastructure
US9703285B2 (en) Fair share scheduling for mixed clusters with multiple resources
US20130311988A1 (en) Migrating virtual machines between networked computing environments based on resource utilization
US8806485B2 (en) Configuring virtual machine images in a networked computing environment
US20130024573A1 (en) Scalable and efficient management of virtual appliance in a cloud
US20190081907A1 (en) Systems and methods for computing infrastructure resource allocation
CN110096489A (en) A kind of data query method, system, device and electronic equipment
US20230010261A1 (en) Dynamic modification of interruptibility settings for network-accessible resources
CN113544647A (en) Capacity management in cloud computing systems using virtual machine family modeling
JP2017091330A (en) Computer system and task executing method of computer system
WO2024051267A1 (en) Capacity management method and related system
US9639140B2 (en) Power management of interactive workloads driven by direct and indirect user feedback
US10148523B1 (en) Resetting computing resources in a service provider network
JP2019082819A (en) System and method for supporting charging for use of accelerator part
CN109213451A (en) The management method and device of storage resource in cloud data system
WO2023179170A1 (en) Instance configuration method and apparatus, and device
US20230325892A1 (en) System and method for managing license of software

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23861970

Country of ref document: EP

Kind code of ref document: A1