CN113946433A

CN113946433A - Resource scheduling method, computing device and storage medium

Info

Publication number: CN113946433A
Application number: CN202010682265.XA
Authority: CN
Inventors: 颜廷帅; 赵宇; 王涛
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2020-07-15
Filing date: 2020-07-15
Publication date: 2022-01-18

Abstract

The embodiment of the application provides a resource scheduling method, a computing device and a storage medium, aiming at created target virtual devices, determining the resource usage amount of the target virtual devices; and under the condition that the resource usage does not meet the resource application amount of the target virtual equipment, directly reestablishing the target virtual equipment according to the resource usage. The created target virtual device is replaced by the newly created target virtual device, the available resources of the newly created target virtual device can meet the resource usage of the target virtual device, and the available resources of the target virtual device can be dynamically adjusted rapidly and automatically under the condition that the current resources cannot be met.

Description

Resource scheduling method, computing device and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a resource scheduling method, a computing device, and a storage medium.

Background

With the rapid development of the internet, compared with the traditional computing service, the cloud service has the advantages of low price, easy expansion, scalability, easy management, high availability and the like, and therefore, the cloud service occupies an increasingly critical position in the information internet era.

Multiple services can be deployed on the cloud server, and multiple cloud services such as model creation, model application, data storage, image analysis and the like can be provided for users. However, many of these services belong to online services, and as long as the services are not offline, the services will occupy resources of the cloud server for a long time, so how to effectively improve resource utilization rate of the online services becomes a crucial problem.

Disclosure of Invention

Aspects of the present disclosure provide a resource scheduling method, a computing device, and a storage medium, which are used to automatically and relatively quickly adjust a suitable resource for utilization.

The embodiment of the application provides a resource scheduling method, which comprises the following steps: determining the resource usage amount of the target virtual equipment aiming at the created target virtual equipment; and under the condition that the resource usage does not meet the resource application amount of the target virtual equipment, directly recreating the target virtual equipment according to the resource usage.

The embodiment of the present application further provides a resource scheduling method, including: determining the resource usage amount of the target virtual equipment aiming at the created target virtual equipment; when the target virtual equipment determines that the resource usage is larger than the resource application amount within a first preset time, receiving a reallocation request sent by the target virtual equipment; and determining whether the number of CPUs in the resource usage carried by the reallocation request meets a preset number and whether the number of memories in the resource usage meets the number of memories in the resource application, and if so, recreating the target virtual device according to the number of CPUs in the resource usage and the number of memories in the resource application.

The embodiment of the present application further provides a resource scheduling method, including: receiving a reallocation request, and determining a new resource application amount directly according to the resource usage amount carried by the reallocation request; and according to the new resource application amount carried by the re-allocation request, re-creating the target virtual equipment for replacing the created target virtual equipment so as to enable the available resource amount of the re-created target virtual equipment to be the resource usage amount.

The embodiment of the present application further provides a resource scheduling method, including: monitoring the resource usage amount of the target virtual equipment; and when the resource usage amount is determined not to meet the resource application amount of the target virtual equipment, sending a reallocation request to a scheduling center, so that the scheduling center determines a new resource application amount according to the resource usage amount carried by the reallocation request, and sends the new resource usage amount to the management equipment through the reallocation request, so that the management equipment recreates the target virtual equipment according to the new resource application amount carried in the reallocation request.

The embodiment of the present application further provides a model deployment method, including: determining the resource usage amount of the target virtual equipment aiming at the created target virtual equipment; under the condition that the resource usage does not meet the resource application amount of the target virtual equipment, the target virtual equipment is directly created again according to the resource usage; deploying a service model based on the re-created target virtual appliance to provide services to the user according to the service model.

An embodiment of the present application further provides a computing device, including: a memory and a processor; the memory for storing a computer program; the processor to execute the computer program to: determining the resource usage amount of the target virtual equipment aiming at the created target virtual equipment; and under the condition that the resource usage does not meet the resource application amount of the target virtual equipment, directly recreating the target virtual equipment according to the resource usage.

An embodiment of the present application further provides a computing device, including: a memory, a processor, and the communication component; the memory for storing a computer program; the processor to execute the computer program to: determining the resource usage amount of the target virtual equipment aiming at the created target virtual equipment; the communication component is used for receiving a reallocation request sent by the target virtual equipment when the target virtual equipment determines that the resource usage is greater than the resource application amount within a first preset time; and the processor is used for determining whether the number of CPUs in the resource usage amount carried by the reallocation request meets a preset number and whether the number of memories in the resource usage amount meets the number of memories in the resource application amount, and if so, re-creating the target virtual equipment according to the number of CPUs in the resource usage amount and the number of memories in the resource application amount.

An embodiment of the present application further provides a computing device, including: a memory and a processor; the memory for storing a computer program; the processor to execute the computer program to: receiving a reallocation request, and determining a new resource application amount directly according to the resource usage amount carried by the reallocation request; and according to the new resource application amount carried by the re-allocation request, re-creating the target virtual equipment for replacing the created target virtual equipment so as to enable the available resource amount of the re-created target virtual equipment to be the resource usage amount.

An embodiment of the present application further provides a computing device, including: a memory, a processor, and a communication component; the memory for storing a computer program; the processor to execute the computer program to: monitoring the resource usage amount of the target virtual equipment; and the communication component is used for sending a reallocation request to a scheduling center under the condition that the resource usage amount is determined not to meet the resource application amount of the target virtual equipment, so that the scheduling center determines a new resource application amount according to the resource usage amount carried by the reallocation request, and sends the new resource usage amount to the management equipment through the reallocation request, so that the management equipment recreates the target virtual equipment according to the new resource application amount carried in the reallocation request.

An embodiment of the present application further provides a computing device, including: a memory, a processor, and a communication component; the memory for storing a computer program; the processor to execute the computer program to: determining the resource usage amount of the target virtual equipment aiming at the created target virtual equipment; under the condition that the resource usage does not meet the resource application amount of the target virtual equipment, the target virtual equipment is directly created again according to the resource usage; deploying a service model based on the re-created target virtual appliance to provide services to the user according to the service model.

Embodiments of the present application also provide a computer-readable storage medium storing a computer program, which when executed by one or more processors causes the one or more processors to implement the steps of the above-mentioned method.

In the embodiment of the application, the resource usage amount of the target virtual equipment is determined aiming at the created target virtual equipment; and under the condition that the resource usage does not meet the resource application amount of the target virtual equipment, directly reestablishing the target virtual equipment according to the resource usage. Therefore, the created target virtual device can be replaced by the newly created target virtual device, the available resources of the newly created target virtual device can meet the resource usage of the target virtual device, and the available resources of the target virtual device can be dynamically adjusted quickly and automatically under the condition that the current resources cannot be met. Meanwhile, the resources are directly adjusted according to the resource usage amount, so that the available resources of the target virtual equipment after being reestablished cannot be excessively wasted, a certain amount of resources can be utilized more appropriately, and the resource utilization rate is improved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

fig. 1 is a schematic structural diagram of a resource scheduling system according to an exemplary embodiment of the present application;

FIG. 2 is a flowchart illustrating a method for scheduling resources according to an exemplary embodiment of the present application;

FIG. 3A is a schematic flowchart illustrating a process of recreating a target virtual device according to an exemplary embodiment of the present application;

FIG. 3B is a flowchart illustrating a process of recreating a target virtual device according to an exemplary embodiment of the present application;

FIG. 3C is a schematic flowchart illustrating a process of recreating a target virtual device according to an exemplary embodiment of the present application;

FIG. 4 is a flowchart illustrating a method for scheduling resources according to an exemplary embodiment of the present application;

FIG. 5 is a flowchart illustrating a method for scheduling resources according to an exemplary embodiment of the present application;

FIG. 6 is a flowchart illustrating a method for scheduling resources according to an exemplary embodiment of the present application;

fig. 7 is a schematic structural diagram of a scheduling apparatus for resources according to another exemplary embodiment of the present application;

fig. 8 is a schematic structural diagram of a scheduling apparatus for resources according to yet another exemplary embodiment of the present application;

fig. 9 is a schematic structural diagram of a scheduling apparatus for resources according to yet another exemplary embodiment of the present application;

fig. 10 is a schematic structural diagram of a scheduling apparatus for resources according to yet another exemplary embodiment of the present application;

FIG. 11 is a schematic block diagram of a computing device provided in an exemplary embodiment of the present application;

FIG. 12 is a schematic block diagram of a computing device provided in an exemplary embodiment of the present application;

FIG. 13 is a schematic block diagram of a computing device provided in an exemplary embodiment of the present application;

fig. 14 is a schematic structural diagram of a computing device according to an exemplary embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

As AI (Artificial Intelligence) has become more popular, more and more users want to improve their service value by the capability of the algorithm model. NLP (Natural Language Processing) and MT (Machine Translation) are two typical fields, and the capabilities provided by the NLP and MT can effectively reduce the labor cost of a user, thereby improving the production efficiency of the user and enabling services thereof. Different on-line service is different from training tasks, and is a resident process, so long as the on-line service is not off-line, resources can be occupied for a long time, and therefore how to effectively improve the resource utilization rate of the on-line service becomes a crucial problem.

A typical solution to model online service resource allocation is to predict the resources that the current model may use before servicing. For example, some platforms allow users to fill in pre-estimated resource amounts for model services, and some platforms predict resource sizes based on empirical values. But the usage amount of the resources can not be dynamically adjusted according to the real load of the model service, if the initial resource prediction is too little, the model service capability is insufficient, and if the estimation is too much, the resource waste is caused.

Therefore, the method provided by the embodiment of the application can automatically and quickly adjust the appropriate resources for utilization.

The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.

Fig. 1 is a schematic structural diagram of a scheduling system of resources according to an exemplary embodiment of the present application. As shown in fig. 1, the system 100 may include: a first device 101 and a second device 102.

The first device 101 may be a device with certain computing capability, and may implement a function of sending a request to the second device 102, and obtain a message that the request is successful from the second device 102. The basic structure of the first device 101 may include: at least one processor. The number of processors may depend on the configuration and type of device with a certain computing power. A device with certain computing capabilities may also include Memory, which may be volatile, such as RAM, non-volatile, such as Read-Only Memory (ROM), flash Memory, etc., or both. The memory typically stores an Operating System (OS), one or more application programs, and may also store program data and the like. In addition to the processing unit and the memory, the device with certain computing capabilities also includes some basic configurations, such as a network card chip, an IO bus, a display component, and some peripheral devices. Alternatively, some peripheral devices may include, for example, a keyboard, a stylus, and the like. Other peripheral devices are well known in the art and will not be described in detail herein. Alternatively, the first device 101 may be a smart terminal, such as a mobile phone, a desktop computer, a notebook, a tablet computer, and the like.

The second device 102 refers to a device that can provide computing processing services in a network virtual environment, and can perform data processing, such as virtual device creation, using a network. It may be implemented to receive the request sent by the first device 101 and return a message that the request of the first device 101 is successful. In physical implementation, the second device 102 may be any device capable of providing computing services, responding to service requests, and returning data processing results, and may be, for example, a cloud server, a cloud host, a virtual center, a regular server, and the like. The second device 102 mainly includes a processor, a hard disk, a memory, a system bus, and the like, and is similar to a general computer architecture.

It should be noted that a plurality of functional modules, virtual devices, and the like, such as the dispatch center 104, the management device 105, the virtual device 106, and the like, may be deployed in the second device 102. In the embodiment of the present application, the first device 101 sends a creation request to the dispatch center 104 in the second device 102. The scheduling center 104 sends a creation request to a management device 105, such as kubernets (for managing containerized applications in cloud servers, making it simple and efficient to deploy containerized applications), for which the management device 105 creates a virtual device 106 based on the request. Furthermore, after creating the virtual device, the management device 105 may send a message that creation is successful to the scheduling center 104, and the scheduling center sends the message to the first device 101 through the second device 102.

The management device 105 determines, for the created target virtual device, a resource usage amount of the target virtual device; and under the condition that the resource usage does not meet the resource application amount of the target virtual equipment, the target virtual equipment is directly created again according to the resource usage to replace the created target virtual equipment, so that the available resource amount of the target virtual equipment created again is the resource usage.

In an application scenario of the embodiment of the present application, the user 103 may perform online translation on the cloud server using a general computing model service, such as the created MT model. The user 103 can also customize a specific computing model on the cloud server, and needs to provide data to train the model and then serve the model to meet the needs of the user. Based on this, the user 103 can do the following:

a user 103 logs in a browser through a first device 101, such as a computer, and pulls a web interface of the browser, the user may create a request through the web interface, the computer responds to an operation of the user and sends a creation request to a scheduling center in a second device 102, such as a scheduling center 104 in a cloud server, the creation request is used for creating a container and is used for creating and deploying a specific computing model, or is used for directly deploying a general model for performing a service of the model, and the request also carries a resource application amount of the user 103 for creating the container. Dispatch center 104, prior to receiving the request, the request may go through load balancing of the cloud servers and an ingress controller to enter the corresponding dispatch center 104. After receiving the request, dispatch center 104 forwards the request to management device 105, such as kubernets. The kubernets creates a virtual device controller, such as a deployment, according to the resource application amount carried in the creation request, where there may be at least two target virtual devices, such as two containers, an a container may be used for creating a model and deploying the model, and a B container may be used for monitoring the resource usage amount of the a container in the controller. After the virtual device controller is created, the user 103 may create and deploy a model on a container in the created virtual device controller, or directly perform machine translation using a generic model already deployed in the container, or the like. The virtual device controller may also be referred to as a model application service. The specific process is similar to the above, and a request, such as a translation request, may also be sent through the web interface, and goes through load balancing of the cloud server and ingress controller to enter into the container that provides the service correspondingly, so that the container receives the request, performs translation, and returns the translation result to the web interface of the user 103.

It should be noted that the B container may also implement other functions, such as a data management function, a user management function, and the like, according to requirements. It should be understood that the requirements are different according to the user 103, such as model deployment, data storage, picture analysis, and the like. The number of target virtual devices may be different, i.e. the target virtual devices in one virtual device controller are different.

When the B container monitors that the resource usage of the a container and the B container (i.e. the virtual device controller to which the B container belongs) is greater than or less than the resource application amount of the container (i.e. the virtual device controller to which the B container belongs) within a certain time, a capacity reduction request or a capacity expansion request is sent to the scheduling center 104, and the resource usage is carried in the request. After receiving the request, dispatch center 104 forwards the request to the management device. The managing device recreates a virtual device controller, such as a deployment, in which there may be two target containers, based on the resource usage in the request. And after the virtual device controller is created again, replacing the original virtual device controller with the virtual device controller, performing the service provided by the original virtual device controller, and destroying the original virtual device controller.

In addition, in addition to direct creation according to the resource usage amount, if the CPU in the resource usage amount is higher than the resource application amount and the memory amount in the resource usage amount is lower than or equal to the resource application amount, the target virtual device may be re-created by modifying only the CPU amount without changing the memory amount, and the creation process is similar to the foregoing and will not be described herein again.

In addition, the scheduling center 104 may also combine the two capacity reduction requests to recreate the target virtual device according to the received two capacity reduction requests. Or, the capacity expansion request may also be received and split, and the request management device 105 creates at least two virtual device controllers to provide services. Specific implementation details will be set forth in detail below. And will not be described in detail herein.

In addition, as can be seen from the foregoing, the translation service may be continuously provided to the user 103 during the process of performing capacity reduction or capacity expansion. User 103 may be a translator of a translation company, a patent agent in a patent agent company. But also enterprises such as patent applicants and database providers, or may be examiners in the patent office. The translation can be performed through the translation service provided by the cloud server. According to the above, the user 103 may provide a translation service interface through a web interface of a computer, input a word to be translated on the interface, and trigger an online translation instruction. The web interface responds to the translation instruction through the computer, sends a translation request to the cloud server, the translation request carries characters to be translated, the translation request is subjected to load balancing of the cloud server, and the ingress controller enters a container which correspondingly provides service, so that the container receives the request, translates the characters to be translated, returns a translation result to the computer web interface of the user 103, and displays the translation result through the computer, and the user 103 obtains the translation result.

In the present embodiment, the devices may all perform network connection, and the network connection may be wireless connection. If the above devices are in communication connection, the network format of the mobile network may be any one of 2G (gsm), 2.5G (gprs), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G + (LTE +), WiMax, 5G, and the like.

The following describes the scheduling process of resources in detail with reference to the method embodiment.

Fig. 2 is a flowchart illustrating a resource scheduling method according to an exemplary embodiment of the present application. The method 200 provided by the embodiment of the present application is executed by a server, for example, a cloud server. More specifically, it may be a scheduling center (also referred to as scheduler) in the server. The method 200 comprises the steps of:

201: and determining the resource usage amount of the target virtual device aiming at the created target virtual device.

202: and under the condition that the resource usage does not meet the resource application amount of the target virtual equipment, directly reestablishing the target virtual equipment according to the resource usage.

The following is detailed for the above steps:

The virtual device refers to an application created by using physical host resources, and provides an isolated operating environment, such as a container. The system can also have a virtual machine, a sandbox and the like under different scenes.

The resource usage amount refers to a resource condition of a physical host used by the target virtual device in the running process. In contrast, a virtual machine may be a virtual resource. The resources may include a Central Processing Unit (CPU) and a memory.

The creating process of the created target virtual device may be:

specifically, a creation request is received, and at least one corresponding target virtual device is created through the management device according to the resource application amount carried in the creation request.

The management device is used for managing containerized applications in the cloud server, and the containerized applications are easy and efficient to deploy, such as kubernets.

FIG. 3A shows a flowchart 300A of recreating a target virtual appliance. For example, as described above, as shown in fig. 3A, a user logs in a web interface created by a model of a cloud server through a computer 101, and the computer 101 sends a creation request to a scheduling center 104 on the cloud server in response to a creation operation of a model service of the user, so as to create the model service, that is, step 301 is executed: a create request is sent to dispatch center 104. And the request carries the resource application amount of the service, such as the amount of 1 CPU (also called 1 core CPU) and 2G memory. After receiving the request, the dispatch center 104 forwards the request to a management device 105, such as kubernets, more specifically, an API (Application Programming Interface) server of kubernets, that is, the dispatch center 104 performs step 302: a create request is sent to the management device 105. And after receiving the request, the API server creates at least one corresponding container according to the resource application amount. That is, the management apparatus 105 performs step 303: a target virtual device is created.

It should be noted that the number of target virtual devices may be different according to the service to be created, such as one container, two containers, three containers, and so on. May be determined by the API server based on the create service.

To facilitate management and control of the target virtual device, the target virtual device may typically be created by a virtual device controller.

Specifically, creating, by the management device, at least one corresponding target virtual device according to the resource application amount carried in the creation request includes: and sending the creating request to the management equipment so that the management equipment creates a corresponding virtual equipment controller according to the resource application amount, wherein the virtual equipment controller is provided with at least one corresponding target virtual equipment.

The virtual device controller refers to a controller for controlling a virtual device, such as a deployment controller for controlling a container, which may also be referred to as a deployment.

For example, as shown in FIG. 3A, the dispatch center sends a create request to a management device, such as an API server of kubernets, as described above. The API server of kubernets creates a deployment controller 3011 according to the resource application amount. The deployment controller 3011 has two containers, a Platform Service 3012 (may be called Platform Service) and a Model Service 3013 (may be called Model Service). The Model Service is responsible for processing Model requests, and specifically can be Model creation and Model deployment, or Model application. Platform Service is responsible for handling various Service logics, specifically, may monitor resource usage of the deployment controller 3011, and may also be referred to as resource usage of the target container.

It should be noted that, for virtual devices belonging to the same deployment controller 3011, the virtual devices may belong to the same pod (deployment unit), and they share the same resource, such as 1 CPU and 2G memory amount.

The method for determining the resource usage amount of the target virtual device may include: and monitoring the resource usage amount of the target virtual equipment through the target virtual equipment, and determining the resource usage amount of the target virtual equipment.

For example, as described above, when a container is created for performing model service, the container may perform model service, and also needs to determine its resource usage, and may query its resource usage through a container resource query command. After inquiring the resource usage amount, the resource usage amount can be sent to the scheduling center, and can be sent in a request form.

It should be noted that, based on the foregoing, when the target virtual device is created by creating a virtual device controller, for example, if the deployment controller has only one container, the determination of the resource usage amount of the deployment is performed by the container.

When the number of the target virtual devices is at least two, the resource usage amounts of the at least two target virtual devices can be monitored through one of the target virtual devices, and the resource usage amounts of the at least two target virtual devices are determined.

Wherein at least two target virtual devices belong to the same virtual device controller.

For example, as described above, when there are at least two virtual devices, such as two containers, Platform Service and Model Service, the Platform Service can be used to monitor the usage amount of the resource. Platform Service can determine the resource usage of the Platform Service and the Model Service by calling a container resource query command, thereby determining the resource usage of the Platform Service and the Model Service, which also belong to the deployment.

It should be noted that the virtual device controller may determine the resource usage amount through the virtual device, that is, the virtual device determines the resource usage amount.

In addition, each virtual device in the virtual device controller may determine its own resource usage amount, and then may determine the sum of the resource usage amounts by any one of the virtual devices, that is, determine the final resource usage amount.

After the target virtual device is created, the user can perform service through the target virtual device, but in the service performing process, the resource usage amount may exceed the resource application amount, and in order to ensure that the service can be performed smoothly, the problem of service breakdown does not occur. Can be completed by the following means:

specifically, the method 200 further includes: determining a limited resource amount larger than the resource usage amount according to the resource usage amount; and according to the limited resource amount, the target virtual equipment is re-created.

The amount of the restricted resource may be determined by the management device, or may be determined by the scheduling center itself. The following may be explained by taking the example of the management device determining the amount of the restricted resource:

for example, as described above, after receiving a request, the API server of kubernets obtains the resource application amount, such as the amount of 1 CPU and 2G memory, from the request. In order to ensure that the service can run smoothly, a resource limit amount (i.e., a limit resource amount) larger than the resource application amount, such as the amount of 1.2 CPUs and 2.1G of memory, may be determined, and then a corresponding container, or deployment, may be created according to the resource limit amount.

It should be noted that, when creating a virtual device, or creating a virtual device controller, the virtual device may be created according to a corresponding preset creation code. In addition, a fixed resource limit amount can also be directly set, but the resource limit amount must be large enough to satisfy any virtual device.

In addition, the scheduling center determines the limited resource amount to recreate the target virtual device, which is similar to the above description and will not be described here again.

And the target virtual device which is created again can be used for replacing the target virtual device which is created already, so that the available resource amount of the target virtual device which is created again is the resource usage amount.

The condition that the resource usage does not satisfy the resource application amount of the target virtual device means that the resource usage exceeds the resource application amount or the resource usage is less than the resource application amount in a majority. The excessive resource application amount is smaller than a certain threshold value of the resource application amount.

For example, as described above, the Platform Service periodically monitors the resource usage amount of the current deployment controller, and when the resource usage amount is monitored to be smaller than the resource application value (i.e., the resource application amount) for a certain period of time (e.g., a preset time, which may be a first preset time below) (or smaller than a certain threshold), sends a capacity reduction request to the scheduling center for capacity reduction. After receiving the capacity reduction request, the scheduling center may send the capacity reduction request to kubernets. After receiving the capacity reduction request, the API server of the kubernetes reconstructs the corresponding container according to the resource usage in the capacity reduction request, then destroys the original container, and continues to operate the model service through the reconstructed container. In addition, a capacity expansion request may also be made, that is, when the resource usage amounts are all greater than the resource application value, the specific implementation process is similar to that described above, and details are not described here.

Wherein, the more specific implementation manner of step 202 is as follows:

specifically, under the condition that the resource usage does not satisfy the resource application amount of the target virtual device, the method for creating the target virtual device again directly according to the resource usage includes: according to the resource usage, performing horizontal expansion or horizontal contraction to recreate the target virtual equipment; or, according to the resource usage, performing vertical capacity expansion or vertical capacity reduction to recreate the target virtual device.

The vertical expansion refers to expansion performed when the number of CPUs in the resource usage is less than or equal to a certain threshold, for example, less than or equal to 1, and the expansion still aims at creating a virtual device controller.

The vertical reduction refers to reduction performed when the number of CPUs in the resource usage is less than or equal to a certain threshold, for example, less than or equal to 1, and the reduction still aims at creating a virtual device controller.

The horizontal expansion refers to expansion performed when the number of CPUs in the resource usage is greater than a certain threshold, for example, greater than 1, and the expansion is performed for creating at least two virtual device controllers.

The horizontal capacity reduction refers to capacity reduction performed when the number of CPUs in the resource usage amounts corresponding to the plurality of virtual device controllers is less than or equal to a certain threshold, for example, less than or equal to 1, where the capacity reduction is performed for merging at least two virtual device controllers into one virtual device controller.

Thus, the capacity expansion and the capacity reduction can be performed based on the number of CPUs. The following may specifically describe the above expansion and contraction:

specifically, under the condition that the resource usage does not satisfy the resource application amount of the target virtual device, the method for creating the target virtual device again directly according to the resource usage includes: and comparing the resource usage amount with the resource application amount through the target virtual equipment, receiving a capacity configuration request sent by the target virtual equipment according to a comparison result, and sending the capacity configuration request to the management equipment so that the management equipment can reestablish the target virtual equipment according to the resource usage amount carried by the capacity configuration request.

Wherein, the comparison result indicates that the resource usage is greater than the resource application amount or less than the resource application amount. And determining capacity reduction or capacity expansion according to different comparison results, so that the management equipment can recreate the target virtual equipment according to a specific request.

The capacity reduction request is as follows:

1) comparing the resource usage amount with the resource application amount through the target virtual equipment, receiving a capacity configuration request sent by the target virtual equipment according to a comparison result, and sending the capacity configuration request to the management equipment, wherein the capacity configuration request comprises: determining that the resource usage is smaller than the resource application amount within a first preset time through the target virtual device, receiving a capacity reduction request sent by the target virtual device, and sending the capacity reduction request to the management device, so that the management device recreates the target virtual device according to the resource usage carried by the capacity reduction request.

It should be noted that the resource usage is smaller than the resource application amount in a certain period of time. The maximum resource usage during the period of time may be selected as the final resource usage during the period of time. Or the minimum resource usage may be selected as the final resource usage for this period of time. Or the average resource usage during the period of time may be selected as the final resource usage during the period of time.

Since the resources may include CPUs, memories, and the like, when determining the resource usage, the final resource usage, such as the average number, the maximum number, and the minimum number of CPUs, may be determined according to the number of CPUs and the number of memories.

For example, as described above, as shown in fig. 3A, Platform Service monitors that the resource usage is always smaller than the resource application amount within a first preset time, e.g., 1 hour. Then, the maximum resource usage is taken as the final resource usage in the first preset time. The Platform Service performs step 304: and sending a capacity reduction request to the dispatching center 104, wherein the capacity reduction request carries the final resource usage amount. After receiving the capability reduction request from Platform Service, the dispatch center 104 sends the capability reduction request to the management device 105, such as an API server of kubernets, and then performs step 305: a capacity reduction request is sent to the management device 105. When the dispatch center 104 sends the capacity reduction request, the capacity reduction request may be a rolling update request for the deployment controller 3011, and update the resource application amount of the deployment controller 3011, and after receiving the request, the API server recreates the deployment controller 3011 according to the final resource usage amount in the request, that is, step 306 is executed: the target virtual device is recreated, at which point the recreated deployment controller 3014 is Version2 (i.e., Version 2). The original deployment controller 3011 is Version1 (i.e., Version 1).

It should be noted that, in the embodiment of the present application, the replication controller is created again by using the rolling update of the replication controller 3011, so that after the replication controller 3014 of Version2 is started, the replication controller 3011 of Version1 destroys the service, thereby ensuring continuous availability of the service. In the case of a reduced volume, the rolling update request is a rolling update for performing the reduced volume as indicated.

rolling update means that the deployment controller 3014 of Version2 is created under the condition that the deployment controller 3011 of Version1 is reserved, and the deployment controller 3011 of Version1 can be destroyed after the creation of the deployment controller 3014 of Version2 is completed, so that the deployment controller 3014 of Version2 replaces the deployment controller 3011 of Version1 to continue service. At this time, the pending data or the pending task sent by the subsequent user is sent to the deployment controller 3014 of Version2 for service operation.

In addition, when capacity expansion is required, the target virtual device is reconstructed in the following manner:

2) comparing the resource usage amount with the resource application amount through the target virtual equipment, receiving a capacity configuration request sent by the target virtual equipment according to a comparison result, and sending the capacity configuration request to the management equipment, wherein the capacity configuration request comprises: and determining that the resource usage is greater than the resource application amount within the second preset time through the target virtual equipment, receiving a capacity expansion request sent by the target virtual equipment, and sending the capacity expansion request to the management equipment, so that the management equipment can reestablish the target virtual equipment according to the resource usage carried by the capacity expansion request.

Wherein, the resource usage is larger than the resource application amount in a period of time. The maximum resource usage during the period of time may be selected as the final resource usage during the period of time. Or the minimum resource usage may be selected as the final resource usage for this period of time. Or the average resource usage during the period of time may be selected as the final resource usage during the period of time.

For example, as described above, as shown in fig. 3A, the newly created Platform Service 3012 (i.e., the Platform Service 3012 in the deployment controller 3014) monitors that the resource usage is always greater than the resource application amount within a second preset time, e.g., 1 hour. Then, the maximum resource usage is taken as the final resource usage in the second preset time. The platform service 3012 performs step 307: and sending a capacity expansion request to the dispatching center 104, wherein the capacity expansion request carries the final resource usage amount. After receiving the capacity expansion request of the platform service 3012, the scheduling center 104 sends the capacity expansion request to the management device 105, for example, an API server of kubernets, and then executes step 308: a capacity expansion request is sent to the management device 105. The capacity expansion request may be a rolling update request for the deployment controller 3011, to update the resource application amount of the deployment controller 3011, after the API server receives the request, the deployment controller 3015 is created again according to the final resource usage amount in the request, that is, step 309 is executed: the target virtual device is recreated, at which point the recreated deployment controller 3015 is Version3 (i.e., Version 3). Here, the rolling update request indicates a request for capacity expansion.

It should be noted that the first preset time may be the same as or different from the second preset time.

In addition, the embodiment of the present application may also implement horizontal expansion of pod by managing HPA (horizontal pod auto retractor) control in the device. A target virtual device, such as a container, may be created by creating a pod. I.e. each pod may have at least one target virtual device, such as two containers, etc.

When the service flow of the user is increased, the resource usage amount can be increased, the number of the pod can be increased through the HPA control, and when the service flow of the user is reduced, the resource usage amount can be reduced, and the number of the pod can be reduced through the HPA control.

However, there are some problems in increasing or decreasing the pod number through the HPA control: for example, increasing the number of pod by the HPA control may adjust the number of pod as the traffic increases, for example, the resource application amount of one pod is 0.2 CPU and 1G memory amount, only one pod initially provides service to the user, and when the traffic increases, the number of pod may increase to 3 because the number of pod is increased and the number of pod is adjusted, that is, the current service occupies the total memory amount of 0.2 × 3 — 0.6 CPU and 1 × 3 — 3G. However, in the actual traffic load, perhaps the number of CPUs needs to be increased to 0.6, but the number of memories does not need to be increased, and the number of memories of only 1G needs to be maintained to satisfy the operation of the service, and at this time, the number of memories of 2G is wasted.

Similarly, the number of pod can be reduced to 1 by the HPA control, but when the traffic is low, the resource usage of even one pod is much smaller than the resource application amount. For example, when creating model service, the memory of resource application amount is 2G, but the actual traffic load only occupies 0.5G of memory amount, and at this time, the HPA control has no way to solve the problem of resource waste in terms of resource scheduling.

And the virtual device controller is directly created through the resource usage amount, so that the waste of resources can be reduced, the resources can be more reasonably and properly utilized, and better service is provided for users.

In order to reasonably utilize resources and not waste unnecessary resources too much, memory resources can be saved in the following manner.

Specifically, the method 200 further includes: determining that the resource usage is greater than the resource application amount within a third preset time through the target virtual device, and receiving a reallocation request sent by the target virtual device; and determining whether the number of CPUs in the resource usage carried by the reallocation request meets a preset number and whether the number of memories in the resource usage meets the number of memories in the resource application, and if so, recreating the target virtual device according to the number of CPUs in the resource usage and the number of memories in the resource application.

Whether the number of CPUs in the resource usage amount satisfies the preset number and whether the number of memories in the resource usage amount satisfies the number of memories in the resource application amount may mean that the number of CPUs is less than or equal to 1. The number of CPUs in the resource usage amount and the number of memories in the resource application amount may be used as a new resource application amount, and a reallocation request may be generated to recreate the target virtual device. The specific embodiments are similar to the above and will not be described herein again. Only the different cases of the above-described resource usage will be explained:

specifically, the method 200 further includes: determining that the resource usage is greater than the resource application amount within a third preset time through the target virtual device, and receiving a reallocation request sent by the target virtual device; and determining that the number of CPUs in the resource usage amount carried by the reallocation request is less than or equal to 1 and the number of memories in the resource usage amount is less than or equal to the number of memories in the resource application amount, taking the number of CPUs in the resource usage amount and the number of memories in the resource application amount as new resource application amounts, sending the reallocation request to the management equipment according to the new resource application amounts, so that the management equipment receives the reallocation request, and reestablishes the target virtual equipment according to the new resource application amounts carried by the reallocation request.

In order to reasonably arrange resources, improve the utilization rate of the resources and not excessively divide the resources, the third preset time can be set to be longer than the second preset time, that is, according to the monitoring for a longer time, the requirement for determining the memory amount can be met by the memory amount in the resource application amount.

The resource usage is larger than the resource application amount in the third preset time. The maximum resource usage during the period of time may be selected as the final resource usage during the period of time. Or the minimum resource usage may be selected as the final resource usage for this period of time. Or the average resource usage during the period of time may be selected as the final resource usage during the period of time.

For example, according to the foregoing, the created Platform Service monitors that the resource usage is always greater than the resource application amount within a third preset time, for example, 5 hours. Then, the maximum resource usage is taken as the final resource usage in the third preset time. The Platform Service sends a redistribution request, which may also be referred to as a capacity expansion request, to the scheduling center, where the redistribution request carries the final resource usage amount. After receiving a Platform Service reallocation request, the scheduling center determines whether the number of resource usage CPUs carried in the request is less than or equal to 1, and if so, continuously checks whether the number of memories is always less than or equal to the number of memories in the resource application amount. If yes, the scheduling center takes the CPU quantity in the resource usage amount and the memory quantity in the resource application amount as a new resource application amount. The dispatch center sends a reallocation request to a management device, such as an API server of kubernetes, where the request carries a new resource application amount. The reallocation request may be a rolling update request for the deployment controller, the resource application amount of the newly created deployment controller is updated, and after receiving the request, the API server creates the deployment controller again according to the new resource application amount in the request. At this time, the newly created deployment controller maintains the original memory amount, does not waste resources too much, and meets the requirements of users.

In addition to the fact that the resource usage is always greater than the resource application amount according to the third preset time, the triggering can be performed according to other triggering conditions, and if the resource usage is greater than the resource application amount and the exceeding portion is greater than a certain threshold value, the reallocation can be also triggered. It should be noted that the third preset time may also be selected to be equal to the second preset time, or different from the second preset time. In addition, in the third preset time, the capacity expansion request can be executed to perform capacity expansion, and similarly, the capacity expansion does not affect the reallocation of the resources in the third preset time. Otherwise, if the CPU is larger than 1, the reallocation may be performed in the following manner, for example, at least two default controllers are created, which is not described herein again.

The above-mentioned situation that the capacity reduction and the capacity expansion are directly performed according to the resource usage amount is eliminated, and appropriate resources, such as the CPU preset amount and the memory preset amount, are added in the resource usage amount in order to ensure that the service requirement can be satisfied as much as possible, reduce the number of times of capacity reduction and capacity expansion, reduce the occurrence of virtual device reconstruction, and save time and resources. Or increasing the CPU preset number and maintaining the memory number in the resource application amount. And then creating the virtual equipment according to the increased resource amount. The specific implementation is similar to the above, and will not be described herein again.

In order to ensure that resources are distributed as evenly as possible and the performance of multiple cores is recycled, when the number of CPUs in the resource usage is greater than 1, the number of the deployment controllers can be determined according to the number of CPUs (or the number of CPU cores).

Specifically, the method 200 further includes: determining that the resource usage is greater than the resource application amount within a third preset time through the target virtual equipment, and receiving a reallocation request sent by the target virtual equipment; the method comprises the steps of increasing the number of CPUs (central processing units) and the number of memories in a resource application amount according to a resource usage amount, determining the number of memories corresponding to each CPU when the increased number of CPUs is larger than 1, sending a corresponding reallocation request to a management device by taking the number of memories corresponding to each CPU as the corresponding reallocation request, enabling the management device to receive the reallocation request, and creating a virtual device controller corresponding to each CPU according to the number of memories corresponding to each CPU, wherein each virtual device controller is provided with at least one corresponding virtual device.

The determination method of the resource usage amount is already determined, and is not described herein again.

The increase of the number of CPUs and the number of memories in the resource application amount according to the resource usage amount may mean that the increased resource application amount may be the same as the resource usage amount, that is, the resource application amount is determined directly according to the resource usage amount. Alternatively, the preset resource amount may be directly increased to the resource usage amount. The following description will be given only by taking as an example that the increased resource application amount can be the same as the resource usage amount:

FIG. 3B shows a flowchart 300B of recreating a target virtual appliance. For example, as described above, as shown in fig. 3B, the created platform service 3012 (i.e., the platform service 3012 in the deployment controller 3011) monitors that the resource usage is always greater than the resource application amount at a third preset time, e.g., 5 hours. Then, the maximum resource usage is taken as the final resource usage in the third preset time. The platform service 3012 performs step 310: and sending a redistribution request, i.e. a capacity expansion request, to the scheduling center 104, where the request carries the final resource usage amount. After receiving the request of the platform service 3012, the scheduling center 104 may determine a new resource application amount according to the resource usage amount, and simultaneously determine whether the number of CPUs is greater than 1, and if the number of CPUs is 2 and the number of memories is 2G, the scheduling center divides the resource usage amount into two groups of new resource application amounts, where each group of new resource application amounts is 1 CPU and 1G of memories. The scheduling center 104 sends a reallocation request to the management device 105, such as an API server of kubernets, based on the two new sets of resource application amounts, that is, step 311 is executed: a reallocation request is sent to the management device 105. The request can carry the two new resource application amounts to create two deployment controllers. Two requests may also be sent, each carrying a new set of resource application amounts. This request may be a rolling update request for the deployment controller 3011, to update the resource application amount of the deployment controller 3011, and after receiving the request, the API server recreates the corresponding deployment controller 3016 and deployment controller 3017 according to each new resource application amount in the request, that is, step 312 is executed: the target virtual device is recreated, with the recreated default controller 3016 being Version4 (i.e., Version4) and the default controller 3017 being Version5 (i.e., Version 5).

When the flow of the user is reduced, the resource usage is monitored to be continuously in a low level (which may be lower than a threshold value of the resource usage), and then an application for reducing the resource usage is sent to the scheduling center. Namely, the reduction can be performed in the above-mentioned reduction manner. When the scheduling center receives two capacity reduction requests at the same time, the two capacity reduction requests can be combined to save resources:

specifically, under the condition that the resource usage does not satisfy the resource application amount of the target virtual device, the method for creating the target virtual device again directly according to the resource usage includes: when at least two capacity reduction requests sent by target virtual equipment are received, combining the at least two capacity reduction requests to obtain a combined capacity reduction request; and according to the merged capacity reduction request, recreating the target virtual equipment.

The merging of at least two capacity reduction requests also requires merging of resource usage therein, so that the capacity reduction requests are created according to the merged capacity reduction requests. The specific creation process has been described above, and will not be described herein. Only the description is as follows:

specifically, under the condition that the resource usage does not satisfy the resource application amount of the target virtual device, the method for creating the target virtual device again directly according to the resource usage includes: when at least two capacity reduction requests are received, combining the at least two capacity reduction requests, and combining the resource usage amount carried in the at least two capacity reduction requests, wherein the combined CPU is less than or equal to 1; and sending a merged capacity reduction request to the management equipment so that the management equipment creates a virtual equipment controller according to the merged resource usage amount carried in the merged capacity reduction request, wherein each virtual equipment controller has at least one corresponding target virtual equipment.

Wherein, the determination method of the resource usage has already been determined, and will not be described herein again.

FIG. 3C shows a flowchart 300C of recreating a target virtual appliance. For example, as described above, as shown in fig. 3C, the platform service 3012 in the created deployment controller 3018 and the platform service 3012 in the created deployment controller 3019 monitor that the resource usage is always less than the resource application amount within a first preset time, such as 1 hour. Then, the maximum resource usage is taken as the final resource usage in the first preset time. The platform service 3012 in the deployment controller 3018 and the platform service 3012 in the deployment controller 3019 each perform step 320: sending a capacity reduction request and step 321: and sending a capacity reduction request to the dispatching center 104, wherein the request carries the final resource usage amount. After receiving the two capacity reduction requests, the dispatch center 104 combines the CPU number and the memory number in the two requests to generate a group of CPU number and memory number. If the number of CPUs is 0.4+ 0.2-0.6, the number of memories is 1+ 1-2G. As the combined resource usage. Based on this, the dispatch center 104 executes sending a merged contraction request to the management device 105, such as API server of kubernets, and executes step 322: a merged condensed capacity request is sent to the management device 105. The request may carry the merged resource usage to create the deployment controller. This request may be a rolling update request merged by the deployment controller 3018 and the deployment controller 3019, and after receiving the request, the API server recreates the corresponding deployment controller 3020 according to the resource application amount merged in the request, that is, step 323 is executed: the target virtual device is recreated, at which point the recreated deployment controller 3020 is Version8 (i.e., Version 8). Among them, the deployment controller 3018 is Version6 (i.e., Version6) and the deployment controller 3019 is Version7 (i.e., Version 7).

After merging the capacity reduction request, if capacity reduction is needed to be continued, the quantity of the CPU and the quantity of the capacity reduction memory can be maintained in the subsequent capacity reduction process, so that the effect of saving resources is achieved, and meanwhile, the normal operation of the service can be kept.

Specifically, the method 200 includes: after the target virtual equipment is re-created by combining the capacity reduction requests, determining that the resource usage amount is smaller than the resource application amount through the re-created target virtual equipment, and receiving the capacity reduction requests sent by the target virtual equipment; and according to the capacity reduction request, the target virtual equipment is re-created.

Similar to what is described above, will not be described in detail. Only the description is as follows:

specifically, the step of receiving a capacity reduction request sent by the target virtual device by determining that the resource usage amount is smaller than the resource application amount through the recreated target virtual device includes: determining that the resource usage amount is smaller than the resource application amount within a first preset time through the re-created target virtual equipment, and receiving a capacity reduction request sent by the target virtual equipment; according to the capacity reduction request, the target virtual device is recreated, and the method comprises the following steps: and taking the memory quantity in the resource usage amount and the CPU quantity in the resource application amount as new resource application amount, sending the capacity reduction request to the management equipment so that the management equipment receives the capacity reduction request, and recreating the target virtual equipment according to the new resource usage amount carried by the capacity reduction request.

It should be noted that the capacity reduction process is similar to the capacity reduction process described above, and therefore, the details are not repeated here. Only to illustrate, after receiving the capacity reduction request, the scheduling center only takes the memory amount in the resource usage amount and the CPU amount in the resource application amount as a new resource application amount, so that, for example, the API server of kubernets performs capacity reduction.

In addition, according to the embodiment of the application, the virtual device can be automatically reconstructed, and the virtual device can interact with the user in the process of establishment, or before and after the establishment, so that the autonomy of the user and the experience of the user are improved.

In order to enable the user to perceive the process of creating the virtual device, the user may be notified when the virtual device is created, such as providing a flow interface created by the user.

Specifically, the method 200 further includes: and in the process of recreating the target virtual device, providing recreating information to the display device to be displayed to the user.

For example, according to the foregoing, when the management device creates the virtual device, the management device may send corresponding creation information, such as creation time, end time, how much the creation is completed currently, for example, 60%, 90%, to the computer of the user through the scheduling center. The user's computer displays the information through a display interface, thereby informing the user.

In addition, the amount of the limited resources can be modified according to the requirements of the user.

Specifically, the method 200 further includes: and receiving a modification request, and modifying the current limited resource quantity of the target virtual equipment according to the limited resource quantity carried in the modification request.

For example, as described above, the dispatch center may receive a modification request from a user computer, where the modification request carries a limited amount of resources. The scheduling center can then limit the amount of resources currently available to the deployment controller. After modification, the modified amount of restricted resources may also be sent to kubernets for deployment controller creation.

When the virtual device is created, if the creation fails, the relevant user can be informed, so that the user can check the failure reason.

Specifically, the method 200 further includes: and when the target virtual equipment is failed to be reestablished, providing a failure message to the target user so that the target user can detect according to the failure message.

For example, according to the foregoing, after the backhaul controller is failed to create a failure, a failure message is sent to the scheduling center, and then the failure message is sent to the computer of the background personnel by the scheduling center, so that the background personnel can detect the reason for the failure.

In addition, the priority can be set for the virtual equipment or the virtual equipment controller, and the capacity expansion or the capacity reduction can be carried out according to the priority, so that the capacity expansion and the capacity reduction can be carried out in sequence under the condition that a large amount of capacity expansion and capacity reduction are concurrent.

Specifically, the method 200 further includes: receiving calibration information, and determining the priority of the created target virtual equipment according to the calibration information; the target virtual appliance is recreated according to the priority.

For example, as described above, the dispatch center can receive the benchmarking information sent by the user's computer, such as the information for setting the priority of the created deployment controller. When the dispatching center receives a plurality of capacity expansion and/or capacity reduction requests, which deployment controller is created can be performed according to the priority in addition to the merged capacity reduction request.

Based on the similar inventive concept, fig. 4 shows a flowchart of a scheduling method of resources according to another exemplary embodiment of the present application. The method 400 provided by the embodiment of the present application is executed by a server, such as a cloud server, and more specifically, a scheduling center (which may also be referred to as a scheduler) in the cloud server.

The method 400 includes the steps of:

401: and determining the resource usage amount of the target virtual device aiming at the created target virtual device.

402: and when the target virtual equipment determines that the resource usage is greater than the resource application amount within the first preset time, receiving a reallocation request sent by the target virtual equipment.

403: and determining whether the number of CPUs in the resource usage carried by the reallocation request meets a preset number and whether the number of memories in the resource usage meets the number of memories in the resource application, and if so, recreating the target virtual device according to the number of CPUs in the resource usage and the number of memories in the resource application.

Since the detailed description of the embodiments of steps 401-403 has been described above, the detailed description is omitted here. Only the description is as follows: the first preset time in step 402 is the third preset time in the preceding paragraph.

In addition, the method 400 further includes: determining that the resource usage is greater than the resource application amount within a first preset time through the target virtual equipment, and receiving a reallocation request sent by the target virtual equipment; the method comprises the steps of increasing the number of CPUs (central processing units) and the number of memories in a resource application amount according to a resource usage amount, determining the number of memories corresponding to each CPU when the increased number of CPUs is larger than 1, sending a corresponding reallocation request to a management device by taking the number of memories corresponding to each CPU as the corresponding reallocation request, enabling the management device to receive the reallocation request, and creating a virtual device controller corresponding to each CPU according to the number of memories corresponding to each CPU, wherein each virtual device controller is provided with at least one corresponding target virtual device.

Further, the method 400 includes: when two capacity reduction requests sent by target virtual equipment are received, the two capacity reduction requests are combined to obtain a combined capacity reduction request; according to the merged capacity reduction request, reestablishing the target virtual equipment; determining that the resource usage amount is smaller than the resource application amount through the target virtual equipment created again, and receiving a capacity reduction request sent by the target virtual equipment; and according to the capacity reduction request, the target virtual equipment is re-created.

Since the foregoing has described in detail the above embodiments, further description is omitted. For illustration only, the second preset time is referred to as the first preset time in the foregoing.

In addition, reference may also be made to various steps in the method 200 described above, where the method 400 is not described in detail.

Based on the similar inventive concept, fig. 5 shows a flowchart of a scheduling method of resources according to another exemplary embodiment of the present application. The method 400 provided by the embodiment of the present application is executed by a server, for example, a cloud server, and more specifically, a management device of a virtual device in the cloud server, for example, kubernets. The method 500 includes the steps of:

501: and receiving a reallocation request, and determining a new resource application amount directly according to the resource usage amount carried by the reallocation request.

502: and according to the new resource application amount carried by the re-allocation request, re-creating the target virtual equipment for replacing the created target virtual equipment so as to enable the available resource amount of the re-created target virtual equipment to be the resource usage amount.

It should be noted that the execution subject of the method 500 may be other applications with management virtual devices besides the specific kubernets. In contrast, a virtual device may have a virtual machine, a sandbox, etc., in addition to the corresponding container. In contrast, method 500 may be performed by having a management device that manages virtual machines, sandboxes, etc.

Since the detailed description of the specific implementation of steps 501-502 has been described above, the detailed description thereof is omitted here. Only the description is as follows: the redistribution request in step 501 may include the capacity reduction request and the capacity expansion request described above, and may also be the redistribution request described above.

Specifically, determining the new resource application amount directly according to the resource usage amount carried by the reallocation request includes: and taking the resource usage amount as a new resource application amount.

It should be noted that the new resource application amount may be determined by the scheduling center, that is, the resource usage amount is used as the new resource application amount by the scheduling center. And sent to the management device by the reallocation request. The new resource application amount can also be determined by the management device itself.

In addition, the method 500 further includes: determining that the number of CPUs in the new resource application amount is greater than 1 through a scheduling center, determining the number of memories corresponding to each CPU, and sending the memory number corresponding to each CPU as a corresponding reallocation request; and receiving a redistribution request, and creating a virtual device controller corresponding to each CPU according to the memory quantity corresponding to each CPU, wherein each virtual device controller has at least one corresponding target virtual device.

In addition, the method 500 further includes: receiving at least two capacity reduction requests through a dispatching center, combining the at least two capacity reduction requests to obtain a combined capacity reduction request, and sending the combined capacity reduction request; and receiving a merged capacity reduction request, and creating a virtual device controller according to the merged resource usage amount carried in the merged capacity reduction request, wherein each virtual device controller has at least one corresponding target virtual device.

Since the foregoing has described in detail the above embodiments, further description is omitted.

In addition, reference may also be made to various steps in the method 200 described above, where the method 500 is not described in detail.

Based on the similar inventive concept, fig. 6 shows a flowchart of a scheduling method of resources according to another exemplary embodiment of the present application. The method 600 provided by the embodiment of the present application is executed by a server, for example, a cloud server, and more specifically, a virtual device, such as a container, in the cloud server. The method 600 includes the steps of:

601: and monitoring the resource usage amount of the target virtual equipment.

602: and when the resource usage amount does not meet the resource application amount of the target virtual equipment, sending a reallocation request to a scheduling center so that the scheduling center determines a new resource application amount according to the resource usage amount carried by the reallocation request, and sending the new resource usage amount to the management equipment through the reallocation request so that the management equipment recreates the target virtual equipment according to the new resource application amount carried in the reallocation request.

Since the detailed description of the specific implementation of steps 601-602 has been described above, it is not repeated here. Only the description is as follows: the redistribution request in step 601 may include the capacity reduction request and the capacity expansion request described above, and may also be the redistribution request described above.

In addition, reference may also be made to the above-mentioned steps of the method 200 for details which are not described in the method 600.

Fig. 7 is a schematic structural framework diagram of a scheduling apparatus of resources according to an exemplary embodiment of the present application. The apparatus 700 may be applied to a server, such as a cloud server, and may specifically be a scheduling center (also referred to as a scheduler) in the cloud server. The apparatus 700 comprises: a determination module 701 and a creation module 702; the following detailed description is directed to the functions of the various modules:

a determining module 701, configured to determine, for the created target virtual device, a resource usage amount of the target virtual device.

A creating module 702, configured to directly create the target virtual device again according to the resource usage amount when the resource usage amount does not satisfy the resource application amount of the target virtual device.

In addition, the creating module 702 is further configured to receive a creating request, and create, according to the resource application amount carried in the creating request, at least one corresponding target virtual device through the management device.

Specifically, the creating module 702 is configured to send a creating request to the management device, so that the management device creates a corresponding virtual device controller according to the resource application amount, where the virtual device controller has at least one corresponding target virtual device.

Specifically, the determining module 701 is configured to monitor the resource usage amount of the target virtual device through the target virtual device, and determine the resource usage amount of the target virtual device.

When the number of the target virtual devices is at least two, the determining module 701 is configured to monitor resource usage amounts of the at least two target virtual devices through one of the target virtual devices, and determine the resource usage amounts of the at least two target virtual devices.

Specifically, the creating module 702 is configured to perform horizontal expansion or horizontal contraction according to the resource usage amount to re-create the target virtual device; or, according to the resource usage, performing vertical capacity expansion or vertical capacity reduction to recreate the target virtual device.

Specifically, the creating module 702 is configured to determine, by the target virtual device, that the resource usage is smaller than the resource application amount within a first preset time, receive a capacity reduction request sent by the target virtual device, and send the capacity reduction request to the management device, so that the management device re-creates the target virtual device according to the resource usage carried by the capacity reduction request.

Specifically, the creating module 702 is configured to determine, by the target virtual device, that the resource usage is greater than the resource application amount within the second preset time, receive a capacity expansion request sent by the target virtual device, and send the capacity expansion request to the management device, so that the management device re-creates the target virtual device according to the resource usage carried in the capacity expansion request.

In addition, the determining module 701 is further configured to determine, according to the resource usage amount, a limited resource amount that is greater than the resource usage amount; a creation module 702 for recreating the target virtual device according to the limited resource amount.

In addition, the apparatus 700 further comprises: the receiving module is used for receiving a reallocation request sent by the target virtual equipment if the target virtual equipment determines that the resource usage is greater than the resource application amount within the third preset time; the determining module 701 is further configured to determine whether the number of CPUs in the resource usage amount carried by the reallocation request satisfies a preset number, and whether the number of memories in the resource usage amount satisfies the number of memories in the resource application amount, and if yes, re-create the target virtual device according to the number of CPUs in the resource usage amount and the number of memories in the resource application amount.

In addition, the receiving module is configured to receive, by the target virtual device, a reallocation request sent by the target virtual device if it is determined that the resource usage amount is greater than the resource application amount within a third preset time; the determining module 701 is further configured to determine that the number of CPUs in the resource usage amount carried in the reallocation request is less than or equal to 1, and the number of memories in the resource usage amount is less than or equal to the number of memories in the resource application amount, and then use the number of CPUs in the resource usage amount and the number of memories in the resource application amount as a new resource application amount, so as to send the reallocation request to the management device according to the new resource application amount, so that the management device receives the reallocation request, and recreates the target virtual device according to the new resource application amount carried in the reallocation request.

In addition, the sending module is further configured to determine, by the target virtual device, that the resource usage amount is greater than the resource application amount within a third preset time, and receive a reallocation request sent by the target virtual device; the determining module 701 is further configured to increase the number of CPUs and the number of memories in the resource application amount according to the resource usage amount, determine the number of memories corresponding to each CPU when the increased number of CPUs is greater than 1, send the number of memories corresponding to each CPU as a corresponding reallocation request to the management device, so that the management device receives the reallocation request, and create a virtual device controller corresponding to each CPU according to the number of memories corresponding to each CPU, where each virtual device controller has at least one corresponding virtual device.

Further, a creation module 702 includes: the merging unit is used for merging at least two capacity reduction requests when receiving the at least two capacity reduction requests sent by the target virtual equipment to obtain merged capacity reduction requests; and the creating unit is used for recreating the target virtual equipment according to the merged capacity reduction request.

In addition, the sending module is further configured to, after the target virtual device is re-created by merging the capacity reduction requests, determine that the resource usage amount is smaller than the resource application amount by the re-created target virtual device, and receive the capacity reduction request sent by the target virtual device; a creating module 702, configured to re-create the target virtual device according to the capacity reduction request.

In addition, the sending module is used for determining that the resource usage amount is smaller than the resource application amount within a first preset time through the target virtual device which is created again, and receiving a capacity reduction request sent by the target virtual device; the creating module 702 is configured to use the memory amount in the resource usage amount and the CPU amount in the resource application amount as a new resource application amount, and send the new resource application amount to the management device through the capacity reduction request, so that the management device receives the capacity reduction request, and re-creates the target virtual device according to the new resource usage amount carried by the capacity reduction request.

Wherein, the virtual device includes: a container.

The target virtual device created again is used to replace the target virtual device created already, so that the available resource amount of the target virtual device created again is the resource usage amount.

In addition, the apparatus 700 further comprises: and the providing module is used for providing the re-creation information to the display equipment to be displayed to the user in the process of re-creating the target virtual equipment.

In addition, the apparatus 700 further comprises: and the modification module is used for receiving the modification request and modifying the current limited resource quantity of the target virtual equipment according to the limited resource quantity carried in the modification request.

In addition, the providing module is configured to provide a failure message to the target user when the target virtual device is failed to be recreated, so that the target user performs detection according to the failure message.

In addition, the determining module 701 is further configured to receive calibration information, and determine the priority of the created target virtual device according to the calibration information; a creation module 702 is further configured to recreate the target virtual device according to the priority.

Fig. 8 is a schematic structural framework diagram illustrating a scheduling apparatus of resources according to another exemplary embodiment of the present application. The apparatus 800 may be applied to a server, such as a cloud server, and may specifically be a scheduling center (also referred to as a scheduler) in the cloud server. The apparatus 800 comprises: the determining module 801 and the sending module 802 are described in detail below with respect to functions of the respective modules:

a determining module 801, configured to determine, for the created target virtual device, a resource usage amount of the target virtual device.

A sending module 802, configured to receive a reallocation request sent by a target virtual device when it is determined, by the target virtual device, that a resource usage amount is greater than a resource application amount within a first preset time.

A determining module 801, configured to determine whether the number of CPUs in the resource usage amount carried by the reallocation request satisfies a preset number, and whether the number of memories in the resource usage amount satisfies the number of memories in the resource application amount, if yes, re-create the target virtual device according to the number of CPUs in the resource usage amount and the number of memories in the resource application amount.

In addition, the sending module 802 is configured to determine, by the target virtual device, that the resource usage amount is greater than the resource application amount within a first preset time, receive a reallocation request sent by the target virtual device; a determining module 801, configured to increase the number of CPUs and the number of memories in the resource application amount according to the resource usage amount, determine, when the increased number of CPUs is greater than 1, the number of memories corresponding to each CPU, send the memory number corresponding to each CPU as a corresponding reallocation request to the management device, so that the management device receives the reallocation request, and create, according to the number of memories corresponding to each CPU, a virtual device controller corresponding to each CPU, where each virtual device controller has at least one corresponding target virtual device.

Further, the apparatus 800 comprises: and the merging module is used for merging the two capacity reduction requests when receiving the two capacity reduction requests sent by the target virtual equipment to obtain a merged capacity reduction request. The creating module is used for recreating the target virtual equipment according to the merged capacity reduction request; the receiving module is used for determining that the resource usage amount is smaller than the resource application amount through the target virtual equipment which is created again and receiving the capacity reduction request sent by the target virtual equipment; and the creating module is used for recreating the target virtual equipment according to the capacity reduction request.

For parts that cannot be mentioned by the apparatus 800, reference may be made to the contents of the apparatus 700 described above.

Fig. 9 is a schematic structural framework diagram illustrating a scheduling apparatus of resources according to another exemplary embodiment of the present application. The apparatus 900 may be applied to a server, for example, a cloud server, and may specifically be a management device of a virtual device in the cloud server, such as kubernets. The apparatus 900 includes: the determining module 901 and the creating module 902 are described in detail below with respect to functions of the respective modules:

the determining module 901 is configured to receive the reallocation request, and determine a new resource application amount directly according to the resource usage amount carried by the reallocation request.

A creating module 902, configured to re-create the target virtual device according to the new resource application amount carried by the re-allocation request, so as to replace the created target virtual device, so that the available resource amount of the re-created target virtual device is the resource usage amount.

Specifically, the determining module 901 is configured to use the resource usage amount as a new resource application amount.

In addition, the determining module 901 is further configured to determine, by the scheduling center, that the number of CPUs in the new resource application amount is greater than 1, determine the number of memories corresponding to each CPU, and send the number of memories corresponding to each CPU as a corresponding reallocation request; the creating module 902 is further configured to receive the reallocation request, and create a virtual device controller corresponding to each CPU according to the amount of memory corresponding to each CPU, where each virtual device controller has at least one corresponding target virtual device.

In addition, the apparatus 900 further comprises: and the merging module is used for receiving the at least two capacity reduction requests through the dispatching center, merging the at least two capacity reduction requests to obtain a merged capacity reduction request and sending the merged capacity reduction request.

In addition, the creating module 902 is further configured to receive a merged reduction request, and create a virtual device controller according to the merged resource usage amount carried in the merged reduction request, where each virtual device controller has at least one corresponding target virtual device.

For parts of the content that cannot be mentioned by the apparatus 900, reference may be made to the content of the apparatus 700 described above.

Fig. 10 is a schematic structural framework diagram illustrating a scheduling apparatus of resources according to another exemplary embodiment of the present application. The apparatus 1000 may be applied to a server, for example, a cloud server, and may specifically be a virtual device, such as a container, in the cloud server. The apparatus 1000 comprises: the monitoring module 1001 and the sending module 1002 are described in detail below with respect to functions of each module:

a monitoring module 1001 configured to monitor resource usage of a target virtual device;

a sending module 1002, configured to send a reallocation request to the scheduling center when it is determined that the resource usage does not satisfy the resource application amount of the target virtual device, so that the scheduling center determines a new resource application amount according to the resource usage carried in the reallocation request, and sends the new resource usage to the management device through the reallocation request, so that the management device recreates the target virtual device according to the new resource application amount carried in the reallocation request.

For parts that cannot be mentioned in the apparatus 1000, reference may be made to the contents of the apparatus 700 described above.

While the internal functions and structures of the apparatus 700 shown in FIG. 7 are described above, in one possible design, the structures of the apparatus 700 shown in FIG. 7 may be implemented as a computing device, such as a server. As shown in fig. 11, the apparatus 1100 may include: memory 1101, processor 1102.

A memory 1101 for storing a computer program.

A processor 1102 for executing a computer program for: determining the resource usage amount of the target virtual equipment aiming at the created target virtual equipment; and under the condition that the resource usage does not meet the resource application amount of the target virtual equipment, directly reestablishing the target virtual equipment according to the resource usage.

Further, the processor 1102 is further configured to: and receiving a creation request, and creating at least one corresponding target virtual device through the management device according to the resource application amount carried in the creation request.

Specifically, the processor 1102 is specifically configured to: and sending the creation request to the management equipment so that the management equipment creates a corresponding virtual equipment controller according to the resource application amount, wherein the virtual equipment controller is provided with at least one corresponding target virtual equipment.

Specifically, the processor 1102 is specifically configured to: and monitoring the resource usage amount of the target virtual equipment through the target virtual equipment, and determining the resource usage amount of the target virtual equipment.

Wherein, when the number of the target virtual devices is at least two, the processor 1102 is specifically configured to: monitoring the resource usage of at least two target virtual devices through one of the target virtual devices, and determining the resource usage of the at least two target virtual devices.

Specifically, the processor 1102 is specifically configured to: according to the resource usage, performing horizontal expansion or horizontal contraction to recreate the target virtual equipment; or, according to the resource usage, performing vertical capacity expansion or vertical capacity reduction to recreate the target virtual device.

Specifically, the processor 1102 is specifically configured to: and comparing the resource usage amount with the resource application amount through the target virtual equipment, receiving a capacity configuration request sent by the target virtual equipment according to a comparison result, and sending the capacity configuration request to the management equipment so that the management equipment can reestablish the target virtual equipment according to the resource usage amount carried by the capacity configuration request.

Specifically, the processor 1102 is specifically configured to: determining that the resource usage is smaller than the resource application amount within a first preset time through the target virtual device, receiving a capacity reduction request sent by the target virtual device, and sending the capacity reduction request to the management device, so that the management device recreates the target virtual device according to the resource usage carried by the capacity reduction request.

Specifically, the processor 1102 is specifically configured to: and determining that the resource usage is greater than the resource application amount within the second preset time through the target virtual equipment, receiving a capacity expansion request sent by the target virtual equipment, and sending the capacity expansion request to the management equipment, so that the management equipment can reestablish the target virtual equipment according to the resource usage carried by the capacity expansion request.

Further, the processor 1102 is further configured to: determining a limited resource amount larger than the resource usage amount according to the resource usage amount; and according to the limited resource amount, the target virtual equipment is re-created.

Further, the processor 1102 is further configured to: determining that the resource usage is greater than the resource application amount within a third preset time through the target virtual device, and receiving a reallocation request sent by the target virtual device; and determining whether the number of CPUs in the resource usage carried by the reallocation request meets a preset number and whether the number of memories in the resource usage meets the number of memories in the resource application, and if so, recreating the target virtual device according to the number of CPUs in the resource usage and the number of memories in the resource application.

Further, the processor 1102 is further configured to: and if the target virtual device determines that the resource usage is greater than the resource application amount within the third preset time, receiving a reallocation request sent by the target virtual device, determining that the number of CPUs in the resource usage carried by the reallocation request is less than or equal to 1, and the number of memories in the resource usage is less than or equal to the number of memories in the resource application amount, taking the number of CPUs in the resource usage and the number of memories in the resource application amount as new resource application amounts, sending the reallocation request to the management device according to the new resource application amounts, so that the management device receives the reallocation request, and reestablishes the target virtual device according to the new resource application amounts carried by the reallocation request.

Further, the processor 1102 is further configured to: determining that the resource usage is greater than the resource application amount within a third preset time through the target virtual equipment, and receiving a reallocation request sent by the target virtual equipment; the method comprises the steps of increasing the number of CPUs (central processing units) and the number of memories in a resource application amount according to a resource usage amount, determining the number of memories corresponding to each CPU when the increased number of CPUs is larger than 1, sending a corresponding reallocation request to a management device by taking the number of memories corresponding to each CPU as the corresponding reallocation request, enabling the management device to receive the reallocation request sent by a scheduling center, and creating a virtual device controller corresponding to each CPU according to the number of memories corresponding to each CPU, wherein each virtual device controller is provided with at least one corresponding virtual device.

In addition, the processor 1102 is specifically configured to: when at least two capacity reduction requests sent by target virtual equipment are received, combining the at least two capacity reduction requests to obtain a combined capacity reduction request; and according to the merged capacity reduction request, recreating the target virtual equipment.

Further, the processor 1102 is further configured to: after the target virtual equipment is re-created by combining the capacity reduction requests, determining that the resource usage amount is smaller than the resource application amount through the re-created target virtual equipment, and receiving the capacity reduction requests sent by the target virtual equipment; and according to the capacity reduction request, the target virtual equipment is re-created.

Further, the processor 1102 is further configured to: determining that the resource usage amount is smaller than the resource application amount within a first preset time through the re-created target virtual equipment, and receiving a capacity reduction request sent by the target virtual equipment; and taking the memory quantity in the resource usage amount and the CPU quantity in the resource application amount as new resource application amount, sending the capacity reduction request to the management equipment so that the management equipment receives the capacity reduction request, and recreating the target virtual equipment according to the new resource usage amount carried by the capacity reduction request.

Wherein, the virtual device includes: a container.

Further, the processor 1102 is further configured to: and in the process of recreating the target virtual device, providing recreating information to the display device to be displayed to the user.

Further, the processor 1102 is further configured to: and receiving a modification request, and modifying the current limited resource quantity of the target virtual equipment according to the limited resource quantity carried in the modification request.

Further, the processor 1102 is further configured to: and when the target virtual equipment is failed to be reestablished, providing a failure message to the target user so that the target user can detect according to the failure message.

Further, the processor 1102 is further configured to: receiving calibration information, and determining the priority of the created target virtual equipment according to the calibration information; the target virtual appliance is recreated according to the priority.

In addition, embodiments of the present invention provide a computer storage medium, and when executed by one or more processors, cause the one or more processors to implement the steps of a method for scheduling resources in the method embodiment of fig. 2.

While the internal functions and structures of the apparatus 800 shown in FIG. 8 are described above, in one possible design, the structures of the apparatus 800 shown in FIG. 8 may be implemented as a computing device, such as a server. As shown in fig. 12, the apparatus 1200 may include: memory 1201, processor 1202, and communications component 1203.

A memory 1201 for storing a computer program.

A processor 1202 for executing a computer program for: and determining the resource usage amount of the target virtual device aiming at the created target virtual device.

A communication component 1203, configured to receive a reallocation request sent by the target virtual device when it is determined that the resource usage amount is greater than the resource application amount within the first preset time by the target virtual device.

The processor 1202 is configured to determine whether the number of CPUs in the resource usage amount carried by the reallocation request satisfies a preset number and whether the number of memories in the resource usage amount satisfies the number of memories in the resource application amount, and if yes, re-create the target virtual device according to the number of CPUs in the resource usage amount and the number of memories in the resource application amount.

Further, the processor 1202 is further configured to: determining that the resource usage is greater than the resource application amount within a first preset time through the target virtual equipment, and receiving a reallocation request sent by the target virtual equipment; the method comprises the steps of increasing the number of CPUs (central processing units) and the number of memories in a resource application amount according to a resource usage amount, determining the number of memories corresponding to each CPU when the increased number of CPUs is larger than 1, sending the memory number corresponding to each CPU as a corresponding reallocation request to a management device so that the management device receives the reallocation request, and creating a virtual device controller corresponding to each CPU according to the memory number corresponding to each CPU, wherein each virtual device controller is provided with at least one corresponding target virtual device.

Further, the processor 1202 is further configured to: when two capacity reduction requests sent by target virtual equipment are received, the two capacity reduction requests are combined to obtain a combined capacity reduction request; according to the merged capacity reduction request, the target virtual equipment is created again; determining that the resource usage amount is smaller than the resource application amount through the target virtual equipment created again, and receiving a capacity reduction request sent by the target virtual equipment; and according to the capacity reduction request, the target virtual equipment is re-created.

It should be noted that, for some contents that the device 1200 cannot refer to, reference may be made to the contents of the device 1100 described above.

In addition, embodiments of the present invention provide a computer storage medium, and when executed by one or more processors, cause the one or more processors to implement the steps of a method for scheduling resources in the method embodiment of fig. 4.

While the internal functions and structures of the apparatus 900 shown in FIG. 9 have been described above, in one possible design, the structures of the apparatus 900 shown in FIG. 9 may be implemented as a computing device, such as a server. As shown in fig. 13, the apparatus 1300 may include: memory 1301, processor 1302.

A memory 1301 for storing a computer program.

A processor 1302 for executing a computer program for: and receiving a reallocation request, and determining a new resource application amount directly according to the resource usage amount carried by the reallocation request.

And according to the new resource application amount carried by the re-allocation request, re-creating the target virtual equipment for replacing the created target virtual equipment so as to enable the available resource amount of the re-created target virtual equipment to be the resource usage amount.

Specifically, the processor 1302 is specifically configured to: and taking the resource usage amount as a new resource application amount.

Further, processor 1302 is further configured to: determining that the number of CPUs in the new resource application amount is greater than 1 through a scheduling center, determining the number of memories corresponding to each CPU, and sending the memory number corresponding to each CPU as a corresponding reallocation request; and receiving a redistribution request, and creating a virtual device controller corresponding to each CPU according to the memory quantity corresponding to each CPU, wherein each virtual device controller has at least one corresponding target virtual device.

Further, processor 1302 is further configured to: and receiving at least two capacity reduction requests through the dispatching center, combining the at least two capacity reduction requests to obtain a combined capacity reduction request, and sending the combined capacity reduction request.

In addition, the device may further include a communication component 1303, configured to receive the merged reduction request, and create one virtual device controller according to the merged resource usage amount carried in the merged reduction request, where each virtual device controller has at least one corresponding target virtual device.

It should be noted that, for some contents that the device 1300 cannot refer to, reference may be made to the contents of the device 1100 described above.

In addition, embodiments of the present invention provide a computer storage medium, and when executed by one or more processors, cause the one or more processors to implement the steps of a method for scheduling resources in the method embodiment of fig. 5.

Having described the internal functionality and structure of the apparatus 1000 shown in FIG. 10, in one possible design, the structure of the apparatus 1000 shown in FIG. 10 may be implemented as a computing device, such as a server. As shown in fig. 14, the apparatus 1400 may include: memory 1401, processor 1402, and communications component 1403.

A memory 1401 for storing the computer program.

A processor 1402 for executing a computer program for: and monitoring the resource usage amount of the target virtual equipment.

A communication component 1403, configured to send, when it is determined that the resource usage amount does not satisfy the resource application amount of the target virtual device, a reallocation request to the scheduling center, so that the scheduling center determines a new resource application amount according to the resource usage amount carried in the reallocation request, and sends the new resource usage amount to the management device through the reallocation request, so that the management device recreates the target virtual device according to the new resource application amount carried in the reallocation request.

It should be noted that, for some contents that the device 1400 fails to mention, reference may be made to the contents of the device 1100 described above.

In addition, embodiments of the present invention provide a computer storage medium, and when executed by one or more processors, cause the one or more processors to implement the steps of a method for scheduling resources in the method embodiment of fig. 6.

Based on the similar inventive concept, another exemplary embodiment of the present application provides a model deployment method. The method 1500 provided by the embodiment of the present application is executed by a server, such as a cloud server, and more specifically, a scheduling center in the cloud server. The method 1500 includes the steps of:

1501: and determining the resource usage amount of the target virtual device aiming at the created target virtual device.

1502: and under the condition that the resource usage does not meet the resource application amount of the target virtual equipment, directly reestablishing the target virtual equipment according to the resource usage.

1503: based on the re-created target virtual appliance, a service model is deployed to provide services to the user in accordance with the service model.

Since the detailed description of the steps 1501-1503 has been described above, the detailed description thereof is omitted here.

The service model comprises an MT model and an NLP model.

In addition, the method 1500 further comprises: receiving a service request, and determining a corresponding service model according to the service request; and obtaining the output information of the determined service model according to the service input information carried by the service request and the determined service model, and returning the output information.

Since the foregoing has been set forth, further description is omitted herein. Only the description is as follows: the input information may be input information of the model, such as a word to be translated, and the output information may be output information of the model, such as a translated word.

In addition, the method 1500 may refer to the steps of the method 200.

Another exemplary embodiment of the present application provides a model deployment apparatus. The apparatus 1600 may be applied to a server, such as a cloud server, and specifically may be a scheduling center in the cloud server. The apparatus 1600 includes: the determining module 1601, the creating module 1602, and the sending module 100 are described in detail below with respect to functions of the respective modules:

a determining module 1601, configured to determine, for the created target virtual device, a resource usage amount of the target virtual device.

A creating module 1602, configured to directly create the target virtual device again according to the resource usage amount when the resource usage amount does not satisfy the resource application amount of the target virtual device.

A deployment module 1603 for deploying the service model based on the re-created target virtual appliance to provide the service to the user according to the service model.

The service model comprises an MT model and an NLP model.

In addition, the determining module 1601 is further configured to receive a service request, and determine a corresponding service model according to the service request; the apparatus 1600 further comprises: and the returning module is used for obtaining the output information of the determined service model according to the service input information carried by the service request and the determined service model and returning the output information.

For parts that cannot be mentioned by the apparatus 1600, reference may be made to the contents of the apparatus 700 described above.

While the internal functionality and structure of apparatus 1600 are described above, in one possible design, the structure of apparatus 1600 may be implemented as a computing device, such as a server. The apparatus 1700 may include: memory 1701, processor 1702.

The memory 1701 is used to store a computer program.

A processor 1702 for executing a computer program for: determining the resource usage amount of the target virtual equipment aiming at the created target virtual equipment; under the condition that the resource usage does not meet the resource application amount of the target virtual equipment, the target virtual equipment is directly created again according to the resource usage; based on the re-created target virtual appliance, a service model is deployed to provide services to the user in accordance with the service model.

The service model comprises an MT model and an NLP model.

Further, the processor 1702 is further configured to: receiving a service request, and determining a corresponding service model according to the service request; and obtaining the output information of the determined service model according to the service input information carried by the service request and the determined service model, and returning the output information.

It should be noted that, for some contents that the device 1700 fails to refer to, reference may be made to the contents of the device 1100 described above.

Additionally, embodiments of the present invention provide a computer storage medium, and when executed by one or more processors, cause the one or more processors to implement the steps of a method for scheduling resources in method 1500.

In addition, in some of the flows described in the above embodiments and the drawings, a plurality of operations are included in a specific order, but it should be clearly understood that the operations may be executed out of the order presented herein or in parallel, and the sequence numbers of the operations, such as 201, 202, 203, etc., are merely used for distinguishing different operations, and the sequence numbers themselves do not represent any execution order. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course, can also be implemented by a combination of hardware and software. With this understanding in mind, the above-described aspects and portions of the present technology which contribute substantially or in part to the prior art may be embodied in the form of a computer program product, which may be embodied on one or more computer-usable storage media having computer-usable program code embodied therein, including without limitation disk storage, CD-ROM, optical storage, and the like.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable multimedia data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable multimedia data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable multimedia data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable multimedia data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

Finally, it should be noted that: the above examples are only intended 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, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A method for scheduling resources, comprising:

determining the resource usage amount of the target virtual equipment aiming at the created target virtual equipment;

and under the condition that the resource usage does not meet the resource application amount of the target virtual equipment, directly recreating the target virtual equipment according to the resource usage.

2. The method of claim 1, further comprising:

and receiving a creation request, and creating at least one corresponding target virtual device through a management device according to the resource application amount carried in the creation request.

3. The method according to claim 2, wherein the creating, by a management device, at least one corresponding target virtual device according to the resource application amount carried in the creation request includes:

and sending the creating request to the management equipment so that the management equipment creates a corresponding virtual equipment controller according to the resource application amount, wherein the virtual equipment controller is provided with at least one corresponding target virtual equipment.

4. The method of claim 1, wherein the determining the resource usage amount of the target virtual device comprises:

and monitoring the resource usage amount of the target virtual equipment through the target virtual equipment, and determining the resource usage amount of the target virtual equipment.

5. The method of claim 4, wherein when the number of the target virtual devices is at least two, the resource usage of at least two target virtual devices is monitored by one of the target virtual devices, and the resource usage of at least two target virtual devices is determined.

6. The method according to claim 1, wherein the recreating the target virtual device directly according to the resource usage amount in the case that the resource usage amount does not satisfy the resource application amount of the target virtual device, comprises:

according to the resource usage, performing horizontal expansion or horizontal contraction to recreate the target virtual equipment; or the like, or, alternatively,

and performing vertical capacity expansion or vertical capacity reduction according to the resource usage amount to recreate the target virtual equipment.

7. The method according to claim 1, wherein the recreating the target virtual device directly according to the resource usage amount in the case that the resource usage amount does not satisfy the resource application amount of the target virtual device, comprises:

and comparing the resource usage amount with the resource application amount through the target virtual equipment, receiving a capacity configuration request sent by the target virtual equipment according to a comparison result, and sending the capacity configuration request to the management equipment, so that the management equipment can reestablish the target virtual equipment according to the resource usage amount carried by the capacity configuration request.

8. The method according to claim 7, wherein the comparing, by the target virtual device, the resource usage amount with the resource application amount, receiving, according to a comparison result, a capacity allocation request sent by the target virtual device, and sending the capacity allocation request to a management device includes:

determining that the resource usage is smaller than the resource application amount within a first preset time through the target virtual equipment, receiving a capacity reduction request sent by the target virtual equipment, and sending the capacity reduction request to the management equipment, so that the management equipment recreates the target virtual equipment according to the resource usage carried by the capacity reduction request.

9. The method according to claim 7, wherein the comparing, by the target virtual device, the resource usage amount with the resource application amount, receiving, according to a comparison result, a capacity allocation request sent by the target virtual device, and sending the capacity allocation request to a management device includes:

determining that the resource usage is greater than the resource application amount within a second preset time through the target virtual equipment, receiving a capacity expansion request sent by the target virtual equipment, and sending the capacity expansion request to the management equipment, so that the management equipment recreates the target virtual equipment according to the resource usage carried by the capacity expansion request.

10. The method of claim 5, wherein the at least two target virtual devices belong to the same virtual device controller.

11. The method of claim 1, 6 or 7, further comprising:

determining a limited resource amount larger than the resource usage amount according to the resource usage amount;

and according to the limited resource amount, recreating the target virtual equipment.

12. The method of claim 1, further comprising:

determining that the resource usage is greater than the resource application amount within a third preset time through the target virtual device, and receiving a reallocation request sent by the target virtual device;

and determining whether the number of CPUs in the resource usage carried by the reallocation request meets a preset number and whether the number of memories in the resource usage meets the number of memories in the resource application, and if so, recreating the target virtual device according to the number of CPUs in the resource usage and the number of memories in the resource application.

13. The method of claim 1, further comprising:

determining that the number of CPUs in the resource usage amount carried by the reallocation request is less than or equal to 1, and the number of memories in the resource usage amount is less than or equal to the number of memories in the resource application amount, taking the number of CPUs in the resource usage amount and the number of memories in the resource application amount as a new resource application amount, sending the reallocation request to the management device according to the new resource application amount, so that the management device receives the reallocation request, and reestablishes the target virtual device according to the new resource application amount carried by the reallocation request.

14. The method of claim 1, further comprising:

determining that the resource usage is greater than the resource application amount within a third preset time through the target virtual equipment, and receiving a reallocation request sent by the target virtual equipment;

and increasing the number of CPUs (central processing units) and the number of memories in the resource application amount according to the resource usage amount, determining the number of memories corresponding to each CPU when the increased number of CPUs is greater than 1, sending a corresponding reallocation request to the management equipment by taking the number of memories corresponding to each CPU as the corresponding reallocation request, so that the management equipment receives the reallocation request, and creating a virtual equipment controller corresponding to each CPU according to the number of memories corresponding to each CPU, wherein each virtual equipment controller is provided with at least one corresponding virtual equipment.

15. The method according to claim 1, wherein the recreating the target virtual device directly according to the resource usage amount in the case that the resource usage amount does not satisfy the resource application amount of the target virtual device, comprises:

when at least two capacity reduction requests sent by target virtual equipment are received, combining the at least two capacity reduction requests to obtain a combined capacity reduction request;

and according to the merged capacity reduction request, recreating the target virtual equipment.

16. The method of claim 15, wherein after recreating the target virtual device via the merged condensed capacity request, the method further comprises:

determining that the resource usage amount is smaller than the resource application amount through the re-created target virtual equipment, and receiving a capacity reduction request sent by the target virtual equipment;

and according to the capacity reduction request, recreating the target virtual equipment.

17. The method of claim 16, wherein the determining, by the re-created target virtual device, that the resource usage amount is smaller than the resource application amount, and receiving the capacity reduction request sent by the target virtual device comprises:

determining that the resource usage amount is smaller than the resource application amount within a first preset time through the re-created target virtual equipment, and receiving a capacity reduction request sent by the target virtual equipment;

the recreating the target virtual device according to the capacity reduction request comprises:

and taking the memory quantity in the resource usage amount and the CPU quantity in the resource application amount as new resource application amount, and sending a capacity reduction request to management equipment so that the management equipment receives the capacity reduction request, and reestablishing the target virtual equipment according to the new resource usage amount carried by the capacity reduction request.

18. The method of any one of claims 1-17, wherein the virtual appliance comprises: a container.

19. The method of any of claims 1-17, wherein the re-created target virtual appliance is used to replace the created target virtual appliance such that the amount of resources available to the re-created target virtual appliance is the amount of resource usage.

20. The method of claim 1, further comprising:

and when the target virtual equipment is failed to be reestablished, providing a failure message to the target user so that the target user can detect according to the failure message.

21. The method of claim 1, further comprising:

receiving calibration information, and determining the priority of the created target virtual equipment according to the calibration information;

and according to the priority, the target virtual equipment is recreated.

22. A method for scheduling resources, comprising:

when the target virtual equipment determines that the resource usage is larger than the resource application amount within a first preset time, receiving a reallocation request sent by the target virtual equipment;

23. The method of claim 22, further comprising:

determining that the resource usage is greater than the resource application amount within a first preset time through the target virtual equipment, and receiving a reallocation request sent by the target virtual equipment;

and increasing the number of CPUs (central processing units) and the number of memories in the resource application amount according to the resource usage amount, determining the number of memories corresponding to each CPU when the increased number of CPUs is greater than 1, sending a corresponding reallocation request to the management equipment by taking the number of memories corresponding to each CPU as the corresponding reallocation request, so that the management equipment receives the reallocation request, and creating a virtual equipment controller corresponding to each CPU according to the number of memories corresponding to each CPU, wherein each virtual equipment controller is provided with at least one corresponding target virtual equipment.

24. The method of claim 23, wherein the method comprises:

when two capacity reduction requests sent by target virtual equipment are received, the two capacity reduction requests are combined to obtain a combined capacity reduction request;

according to the merged capacity reduction request, reestablishing the target virtual equipment;

25. A method for scheduling resources, comprising:

receiving a reallocation request, and determining a new resource application amount directly according to the resource usage amount carried by the reallocation request;

26. The method of claim 25, wherein the determining a new resource application amount directly from the resource usage amount carried by the reallocation request comprises:

and taking the resource usage amount as a new resource application amount.

27. The method of claim 25, further comprising:

determining that the number of CPUs in the new resource application amount is greater than 1 through a scheduling center, determining the number of memories corresponding to each CPU, and sending the memory number corresponding to each CPU as a corresponding reallocation request;

and receiving the redistribution request, and creating a virtual device controller corresponding to each CPU according to the memory quantity corresponding to each CPU, wherein each virtual device controller has at least one corresponding target virtual device.

28. The method of claim 25, further comprising:

receiving at least two capacity reduction requests through a dispatching center, combining the at least two capacity reduction requests to obtain a combined capacity reduction request, and sending the combined capacity reduction request;

and receiving the merged capacity reduction request, and creating a virtual device controller according to the merged resource usage amount carried in the merged capacity reduction request, wherein each virtual device controller has at least one corresponding target virtual device.

29. A method for scheduling resources, comprising:

monitoring the resource usage amount of the target virtual equipment;

and when the resource usage amount is determined not to meet the resource application amount of the target virtual equipment, sending a reallocation request to a scheduling center, so that the scheduling center determines a new resource application amount according to the resource usage amount carried by the reallocation request, and sends the new resource usage amount to the management equipment through the reallocation request, so that the management equipment recreates the target virtual equipment according to the new resource application amount carried in the reallocation request.

30. A method for deploying a model, comprising:

under the condition that the resource usage does not meet the resource application amount of the target virtual equipment, the target virtual equipment is directly created again according to the resource usage;

deploying a service model based on the re-created target virtual appliance to provide services to the user according to the service model.

31. The method according to claim 30, wherein the service models comprise an MT model and an NLP model.

32. The method of claim 30, further comprising:

receiving a service request, and determining a corresponding service model according to the service request;

and obtaining the output information of the determined service model according to the service input information carried by the service request and the determined service model, and returning the output information.

33. A computing device, comprising: a memory and a processor;

the memory for storing a computer program;

the processor to execute the computer program to:

34. A computing device, comprising: a memory, a processor, and the communication component;

the memory for storing a computer program;

the processor to execute the computer program to:

the communication component is used for receiving a reallocation request sent by the target virtual equipment when the target virtual equipment determines that the resource usage is greater than the resource application amount within a first preset time;

and the processor is used for determining whether the preset quantity is met or not and whether the memory quantity in the resource usage quantity meets the memory quantity in the resource application quantity or not, and if so, re-establishing the target virtual equipment according to the CPU quantity in the resource usage quantity and the memory quantity in the resource application quantity.

35. A computing device, comprising: a memory and a processor;

the memory for storing a computer program;

the processor to execute the computer program to:

36. A computing device, comprising: a memory, a processor, and a communication component;

the memory for storing a computer program;

the processor to execute the computer program to: monitoring the resource usage amount of the target virtual equipment;

and the communication component is used for sending a reallocation request to a scheduling center under the condition that the resource usage amount is determined not to meet the resource application amount of the target virtual equipment, so that the scheduling center determines a new resource application amount according to the resource usage amount carried by the reallocation request, and sends the new resource usage amount to the management equipment through the reallocation request, so that the management equipment recreates the target virtual equipment according to the new resource application amount carried in the reallocation request.

37. A computing device, comprising: a memory, a processor, and a communication component;

the memory for storing a computer program;

the processor to execute the computer program to: determining the resource usage amount of the target virtual equipment aiming at the created target virtual equipment;

38. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by one or more processors, causes the one or more processors to perform the steps of the method of any one of claims 1-32.