KR-20260062426-A - Method and cloud system for securing cluster high availability using node packing and resource rescheduling

KR20260062426AKR 20260062426 AKR20260062426 AKR 20260062426AKR-20260062426-A

Abstract

A method and system for securing high availability of a cluster using node packing and resource rescheduling are disclosed. A method for securing high availability of a cluster using node packing and resource rescheduling, performed in a cloud system according to one aspect of the present invention, comprises the steps of: collecting monitoring information regarding the status of available resources of each node constituting the cluster; classifying available resources by node by identifying unused resources; selecting a node to secure high availability as a target node based on available resources; and creating a high-availability node by rescheduling the resources used by the target node to another node based on information regarding available resources by node.

Inventors

반일권
홍성철
이승윤
권경민
김명진

Assignees

주식회사 이노그리드

Dates

Publication Date: 20260507
Application Date: 20241029

Claims (12)

In a method for ensuring cluster high availability performed in a cloud system, A step of collecting monitoring information on the status of available resources of each node constituting the cluster; A step of identifying unused resources and classifying available resources by node; A step of selecting a node to secure high availability based on the above available resources as a target node; and A method for ensuring high availability of a cluster using node packing and resource rescheduling, comprising the step of creating a high-availability node by rescheduling the resources used by the target node to another node based on information regarding available resources per node.
In claim 1, A cluster high availability method using node packing and resource rescheduling, further comprising the step of isolating the above high availability nodes so that resources are allocated only to pre-configured high-use tasks.
In claim 2, A cluster high availability method using node packing and resource rescheduling, wherein the high availability node is switched to standby mode when a preset waiting time elapses after isolation, and the standby mode is released when the high availability task is requested.
In claim 3, A cluster high availability method using node packing and resource rescheduling, which sets the waiting time of a new target node differently depending on the number of high availability nodes that are previously isolated or in standby mode.
In claim 2, A cluster high availability method using node packing and resource rescheduling, wherein when multiple of the above high availability nodes are created, the rest are switched to standby mode except for some.
In claim 5, A cluster high availability method using node packing and resource rescheduling, which determines the target number of high availability nodes by artificial intelligence analysis of resource usage history for each node.
In claim 6, A method for ensuring high availability of a cluster using node packing and resource rescheduling, wherein if it is not possible to create the above-mentioned target number of high availability nodes, one or more candidate nodes are selected based on information regarding available resources, and the candidate nodes are excluded from scheduling for new tasks until the use of resources currently in use is released and they are converted into high availability nodes.
A computer program stored on a computer-readable medium for performing a method to ensure cluster high availability using node packing and resource rescheduling, wherein the computer program causes the computer to perform the following steps, and said steps are, A step of collecting monitoring information on the status of available resources of each node constituting the cluster; A step of identifying unused resources and classifying available resources by node; A step of selecting a node to secure high usability based on the above available resources as a target node; and A computer program stored on a computer-readable medium, comprising the step of creating a high-availability node by rescheduling the resources used by the target node to another node based on information regarding available resources per node.
A resource monitor unit that collects monitoring information on the status of available resources of each node constituting the cluster; A resource management unit that identifies unused resources to classify available resources per node and selects a node to secure high availability based on the available resources as a target node; and A cluster high availability cloud system using node packing and resource rescheduling, comprising a scheduling unit that creates a high availability node by rescheduling the resources used by the target node to another node based on information regarding available resources per node.
In claim 9, A cluster high availability cloud system using node packing and resource rescheduling, wherein the scheduling unit isolates the high availability nodes so that resources are allocated only to pre-configured high-use tasks, and switches the remainder to standby mode except for some when a pre-configured waiting time elapses after isolation or when multiple high availability nodes are created.
In claim 9, A cluster high availability cloud system using node packing and resource rescheduling, wherein the resource management unit determines the target number of high availability nodes based on artificial intelligence analysis of resource usage history for each node.
In claim 11, If the above resource management unit is unable to create the above target number of high-availability nodes, it selects one or more candidate nodes based on information regarding available resources, and A cluster high availability cloud system using node packing and resource rescheduling, wherein the scheduling unit excludes the candidate node from scheduling new tasks until the use of resources currently in use is released and it is switched to the high availability node.

Description

Method and cloud system for securing cluster high availability using node packing and resource rescheduling The present invention relates to cloud technology, and more specifically, to a method and system for securing cluster high availability using node packing and resource rescheduling. Kubernetes is an orchestration tool that facilitates the efficient management and deployment of container runtimes, such as Docker, across clusters composed of multiple servers. It is a recently emerging technology that extends from traditional methodologies of processing requests on a single server to provide uninterrupted service across multiple servers. Kubernetes views a Pod as the smallest unit of program deployment, and when a request for deployment of a Pod arrives, the Kubernetes scheduler scores it by considering various factors to determine which node (server) the Pod will be deployed to. However, when there are multiple scheduleable nodes, scheduling tends to be distributed. By default, the Kubernetes scheduler schedules based on minimum resource usage, spread placement, and consideration of various requirements. It prefers nodes with low usage, attempts to maintain cluster resources in balance, distributes Pods across the cluster to prevent work concentration on specific nodes, and determines the optimal placement location by comprehensively considering the Pod's requirements and the node's characteristics. FIG. 1 is a schematic diagram illustrating a cloud system for securing cluster high availability according to an embodiment of the present invention. FIG. 2 is a functional block diagram illustrating the configuration of a resource management system that secures high availability using node packing and resource rescheduling according to an embodiment of the present invention. FIG. 3 is a flowchart illustrating a process for ensuring high availability performed in a resource management system according to an embodiment of the present invention. FIG. 4 is a flowchart illustrating the operation process of a high availability node according to an embodiment of the present invention. FIG. 5 is a flowchart illustrating the process of securing a target number of high-availability nodes according to an embodiment of the present invention. FIGS. 6 to 12 are exemplary diagrams illustrating a method of securing cluster high availability using node packing and resource rescheduling according to an embodiment of the present invention. FIGS. 13 to 18 are exemplary drawings illustrating a method of operation within a cloud system according to an embodiment of the present invention. The present invention is capable of various modifications and may have various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the invention to specific embodiments, and it should be understood that the invention includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the invention. When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Terms such as "first," "second," etc., may be used to describe various components, but said components should not be limited by said terms. These terms are used solely for the purpose of distinguishing one component from another. For example, terms such as "first threshold," "second threshold," etc., to be described later may be pre-designated as thresholds that are substantially different or partially identical; however, since there is a possibility of confusion when expressed using the same word "threshold," the terms "first," "second," etc., will be used together for the convenience of distinction. The terms used herein are merely for describing specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as “comprising” or “having” are intended to indicate the presence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. Furthermore, the components of the embodiments described with reference to each drawing are not limited to the respective embodiments and may be implemented to be included in other embodiments within the scope of maintaining the technical spirit of the present invention. It is also obvious that multiple