CN-121996360-A - Instance scheduling method and device, hybrid scheduling component, storage medium and product

CN121996360ACN 121996360 ACN121996360 ACN 121996360ACN-121996360-A

Abstract

The application provides an instance scheduling method, an instance scheduling device, a mixed scheduling component, a computer readable storage medium and a computer program product, wherein the method is applied to the mixed scheduling component, the mixed scheduling component is used for managing resources of a plurality of mixed nodes, the plurality of mixed nodes are computing nodes supporting a plurality of types of runtime instances in a cluster, the types of the runtime instances comprise virtual machines and containers, the method comprises the steps of receiving scheduling requests of mixed services sent by clients, obtaining each resource state of each computing node in the cluster, generating an initial scheduling solution set according to component composition information and component resource requirements contained in each resource state and the scheduling request, wherein each scheduling solution in the initial scheduling solution set represents a deployment scheme for deploying the plurality of component instances on different computing nodes, selecting a target scheduling solution from the initial scheduling solution set, and creating the plurality of component instances on the computing nodes corresponding to the target scheduling solution.

Inventors

JI DALONG
LI XIAOMAN
QIAN LING
JIA YU

Assignees

中移(苏州)软件技术有限公司
中国移动通信集团有限公司

Dates

Publication Date: 20260508
Application Date: 20260408

Claims (10)

1. An instance scheduling method, applied to a hybrid scheduling component, where the hybrid scheduling component is configured to manage resources of a plurality of hybrid nodes, where the plurality of hybrid nodes are computing nodes that support multiple types of runtime instances in a cluster, and the types of runtime instances include virtual machines and containers, and the method includes: Receiving a scheduling request of mixed service sent by a client, wherein the scheduling request is used for indicating a plurality of component instances to be deployed on a computing node; acquiring each resource state of each computing node in the cluster; Generating an initial scheduling solution set according to the resource state and the component composition information and the component resource requirement contained in the scheduling request, wherein each scheduling solution in the initial scheduling solution set represents a deployment scheme for deploying a plurality of component instances on different computing nodes; selecting a target scheduling solution from the initial scheduling solution set; And creating a plurality of component instances on the computing nodes corresponding to the target scheduling solutions.
2. The method of claim 1, wherein generating the initial set of scheduling solutions based on each of the resource status and component composition information and component resource requirements contained in the scheduling request comprises: Screening candidate computing nodes from all computing nodes in the cluster according to the resource state and the resource requirement corresponding to each component instance in the component resource requirements; Generating N groups of random scheduling results as an initial scheduling solution set according to the number Z of the components and the number K of candidate computing nodes included in the component composition information, wherein each scheduling solution in the initial scheduling solution set is an array with the length Z, each element in the array represents the number of the computing node to be deployed corresponding to a component instance, and Z, K and N are positive integers.
3. The method of claim 1, wherein the selecting a target scheduling solution from the initial set of scheduling solutions comprises: generating an association matrix of the components according to the association relation among the components contained in the scheduling request; calculating the resource occupation state of a plurality of component instances on corresponding calculation nodes aiming at each scheduling solution to obtain a service evaluation index of each scheduling solution; Generating each indication parameter for each scheduling solution, wherein each indication parameter is used for determining whether an ith component instance and a jth component instance are scheduled to the same computing node, and i and j are positive integers; and selecting one target scheduling solution from the initial scheduling solution set according to each indication parameter, the elements in the incidence matrix and the service evaluation index of each scheduling solution.
4. The method of claim 3, wherein said selecting one of said target scheduling solutions from said initial set of scheduling solutions based on each of said indication parameters, an element in said correlation matrix, and a traffic evaluation indicator for each of said scheduling solutions comprises: Generating each association index according to each indication parameter and an element in the association matrix, wherein the element represents the association degree between the ith component instance and the jth component instance, and each association index represents an association degree score when the ith component instance and the jth component instance are scheduled to the same computing node; Determining a comprehensive score of each scheduling solution according to the service evaluation index of each scheduling solution and each association index; And selecting a scheduling solution with the comprehensive score larger than a threshold value from the initial scheduling solution set as the target scheduling solution according to the comprehensive score of each scheduling solution.
5. The method of claim 3, wherein calculating, for each of the scheduling solutions, a resource occupancy state of the plurality of component instances on the corresponding computing node, to obtain the traffic evaluation index of each of the scheduling solutions, includes: determining the occupancy rate of the resources applied by all the component instances scheduled to each computing node to the residual resources of each computing node; Determining the service score of each computing node according to the occupancy rate corresponding to each computing node; and calculating the average value of the service scores of all the calculation nodes, and taking the average value as the service evaluation index of each scheduling solution.
6. The method of claim 5, wherein determining the traffic score of each computing node according to the occupancy corresponding to each computing node comprises: when the occupancy rate is smaller than or equal to a first threshold value, determining the service score of each computing node as a first score; when the occupancy rate is greater than or equal to a second threshold value, determining that the service score of each computing node is a second score; and when the occupancy rate is larger than the first threshold value and smaller than the second threshold value, determining the service score of each computing node as a third score according to the first threshold value by utilizing a linear interpolation algorithm.
7. An instance scheduling apparatus, applied to a hybrid scheduling component, the hybrid scheduling component configured to manage resources of a plurality of hybrid nodes, the plurality of hybrid nodes being computing nodes supporting multiple classes of runtime instances within a cluster, the types of runtime instances including virtual machines and containers, the apparatus comprising: The system comprises a receiving unit, a scheduling request receiving unit, a receiving unit and a scheduling unit, wherein the receiving unit is used for receiving a scheduling request of mixed service sent by a client, and the scheduling request is used for indicating a plurality of component instances to be deployed on a computing node; An obtaining unit, configured to obtain each resource state of each computing node in the cluster; The processing unit is used for generating an initial scheduling solution set according to the resource state and the component composition information and the component resource requirement contained in the scheduling request, wherein each scheduling solution in the initial scheduling solution set represents a deployment scheme for deploying a plurality of component instances on different computing nodes; The processing unit is used for selecting a target scheduling solution from the initial scheduling solution set; And the processing unit is used for creating a plurality of component instances on the computing nodes corresponding to the target scheduling solutions.
8. A hybrid scheduling assembly, the hybrid scheduling assembly comprising: A memory for storing computer executable instructions or computer programs; A processor for implementing the method of any of claims 1 to 6 when executing computer executable instructions or computer programs stored in the memory.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

Description

Instance scheduling method and device, hybrid scheduling component, storage medium and product Technical Field The present application relates to cloud computing technology, and in particular, to an example scheduling method, an example scheduling device, a hybrid scheduling component, a computer readable storage medium, and a computer program product. Background Generally, the virtual machine and the container belong to two independent management structures, and are scheduled to the physical machines managed by the corresponding management components. With the rapid development of kubernetes cloud native technology, more and more services begin to be transformed in a containerized manner, but a complete service is composed of many different service components, and most enterprises still have a large number of service components deployed in virtual machines, so a scheduling scheme for supporting the mixing of containers and virtual machines is urgently needed. At present, at least virtual machines and containers are managed by different systems respectively, so that the problems of resource waste and inconsistent scheduling are caused. Disclosure of Invention The embodiment of the application provides an example scheduling method, an example scheduling device, a hybrid scheduling component, a computer readable storage medium and a computer program product. The technical scheme of the embodiment of the application is realized as follows: the embodiment of the application provides an instance scheduling method, which is applied to a hybrid scheduling component, wherein the hybrid scheduling component is used for managing resources of a plurality of hybrid nodes, the plurality of hybrid nodes are computing nodes supporting multiple types of runtime instances in a cluster, the types of the runtime instances comprise virtual machines and containers, and the method comprises the following steps: Receiving a scheduling request of mixed service sent by a client, wherein the scheduling request is used for indicating a plurality of component instances to be deployed on a computing node; acquiring each resource state of each computing node in the cluster; Generating an initial scheduling solution set according to the resource state and the component composition information and the component resource requirement contained in the scheduling request, wherein each scheduling solution in the initial scheduling solution set represents a deployment scheme for deploying a plurality of component instances on different computing nodes; selecting a target scheduling solution from the initial scheduling solution set; And creating a plurality of component instances on the computing nodes corresponding to the target scheduling solutions. The embodiment of the application provides an instance scheduling device, which is applied to a hybrid scheduling component, wherein the hybrid scheduling component is used for managing resources of a plurality of hybrid nodes, the plurality of hybrid nodes are computing nodes supporting multiple types of runtime instances in a cluster, the types of the runtime instances comprise virtual machines and containers, and the device comprises: The system comprises a receiving unit, a scheduling request receiving unit, a receiving unit and a scheduling unit, wherein the receiving unit is used for receiving a scheduling request of mixed service sent by a client, and the scheduling request is used for indicating a plurality of component instances to be deployed on a computing node; An obtaining unit, configured to obtain each resource state of each computing node in the cluster; The processing unit is used for generating an initial scheduling solution set according to the resource state and the component composition information and the component resource requirement contained in the scheduling request, wherein each scheduling solution in the initial scheduling solution set represents a deployment scheme for deploying a plurality of component instances on different computing nodes; The processing unit is used for selecting a target scheduling solution from the initial scheduling solution set; And the processing unit is used for creating a plurality of component instances on the computing nodes corresponding to the target scheduling solutions. The embodiment of the application provides a hybrid scheduling component, which comprises: A memory for storing computer executable instructions or computer programs; And the processor is used for realizing the method provided by the embodiment of the application when executing the computer executable instructions or the computer programs stored in the memory. The embodiment of the application provides a computer readable storage medium storing a computer program or computer executable instructions for implementing the example scheduling provided by the embodiment of the application when being executed by a processor. Embodiments of the present application provide a com