Container cross-cluster capacity scaling

Patent metadata

Field	Value
Publication number	US-12572393-B2
Application number	US-202218052993-A
Country	US
Kind code	B2
Filing date	Nov 7, 2022
Priority date	Nov 7, 2022
Publication date	Mar 10, 2026
Grant date	Mar 10, 2026

Abstract

A method, computer program product, and computer system are provided for container cross-cluster capacity scaling. The method includes broadcasting local capacity information of capacity availability or capacity requirement for the local cluster and receiving broadcasts from each of one or more other clusters providing capacity information including capacity availability or capacity requirements. The method may map the received capacity information with the local capacity information and may determine a suitable cross-cluster capacity sharing when a capacity requirement of the local cluster maps to a capacity availability of another cluster or when a capacity availability of the local cluster maps to a capacity requirement of another cluster. The method may coordinate the deallocation of a node from the cluster having the capacity availability and reallocation of the node to the cluster having the capacity requirement.

First claim

What is claimed is:

1 . A computer-implemented method for container cross-cluster capacity scaling, said method is carried at a local cluster having one or more current nodes in the form of physical or virtual machines running containers and comprises:
broadcasting local capacity information of capacity availability or capacity requirement for the local cluster; receiving broadcasts from each of one or more other clusters providing capacity information including capacity availability or capacity requirement; mapping the received capacity information with the local capacity information; defining a time frame for determining if a suitable cross-cluster capacity sharing is possible; storing metadata of workflow patterns in the form of the capacity information for the local cluster in a key-value data metadata store in a control plane of each of the local cluster and the other clusters, determining capacity utilization trends for the local cluster based on the metadata and the mapping; and applying predictive modeling based on the capacity utilization trends to the mapping, wherein on determining that a capacity requirement of the local cluster is not met by received capacity availability of the one or more other clusters within the defined time frame, coordinating allocation of a node to the local cluster by local cluster scaling, and wherein on determining that a capacity requirement of the local cluster maps to a capacity availability of a first cluster or that a capacity availability of the local cluster maps to a capacity requirement of a second cluster within the time defined time frame, coordinating deallocation of a node from the first cluster having the capacity availability and reallocation of the node to the second cluster having the capacity requirement.

2 . The method of claim 1 , wherein the local capacity information and the received capacity information include temporary periods of availability or requirement, and
wherein the mapping is based on the temporary periods of availability and requirement.

3 . The method of claim 1 , wherein determining a suitable cross-cluster capacity sharing includes applying supply and demand algorithms used to understand the capacity availability and capacity requirements and using a rules-based scheduler to match the supply and demand algorithms.

4 . The method of claim 1 , including gathering local capacity information from an agent running at each node at the local cluster.

5 . The method of claim 1 , including updating account billing and providing billing sharing beyond account boundaries when coordinating a node deallocation and reallocation.

6 . The method of claim 1 , wherein the method is carried out in a control plane of a cluster including defined custom resource application programming interfaces (APIs) providing at least some of the method functions.

7 . The method of claim 6 , wherein the defined custom resource APIs on each cluster communicate with similar peer defined custom resource APIs on other clusters and the defined custom resource APIs communicate with each other and other components using container orchestration APIs.

8 . A system for container cross-cluster capacity scaling, comprising:
a processor and a memory configured to provide computer program instructions to the processor to execute functions of components of a cross-cluster capacity component including: a capacity broadcast component for broadcasting local capacity information of capacity availability or capacity requirement for a local cluster; a broadcast receiving component for receiving broadcasts from each of one or more other clusters providing capacity information including capacity availability or capacity requirements; a capacity mapping component for mapping the received capacity information with the local capacity information; a defining component for defining a time frame for determining if a suitable cross-cluster capacity sharing is possible; a metadata storing component for storing metadata of workflow patterns in the form of the capacity information for the local cluster in a key-value data metadata store in a control plane of each of the local cluster and the other clusters; a capacity trend component for determining capacity utilization trends for the local cluster based on the metadata and the mapping; and a predictive modeling component for applying predictive modeling based on the capacity utilization trends to the mapping, wherein on determining, by a capacity allocation component, that a capacity requirement of the local cluster is not met by received capacity availability of the one or more other clusters within the defined time frame, coordinating allocation of a node to the local cluster by local cluster scaling, and wherein on determining that a capacity requirement of the local cluster maps to a capacity availability of a first cluster or that a capacity availability of the local cluster maps to a capacity requirement of a second cluster within the time defined time frame, coordinating deallocation of a node from the first cluster having the capacity availability and reallocation of the node to the second cluster having the capacity requirement.

9 . The system of claim 8 ,
wherein the local capacity information and the received capacity information include temporary periods of availability or requirement, and wherein the capacity allocation component includes a temporary node period component for applying the temporary periods of availability and requirement.

10 . The system of claim 8 , including a supply/demand component for applying supply and demand algorithms used to understand the capacity availability and capacity requirements and a rules-based scheduler component for using a rules-based scheduler to match the supply and demand algorithms.

11 . The system of claim 8 , including a gathering component for gathering local capacity information from an agent running at each node at the local cluster.

12 . The system of claim 8 , including a capacity metering component for updating account billing and providing billing sharing beyond account boundaries when coordinating a node deallocation and reallocation.

13 . The system of claim 8 , wherein the capacity allocation component includes using a custom resource definition application programming interface (API) for deallocating nodes from a cluster and reallocating nodes to a cluster.

14 . The system of claim 8 , wherein the cross-cluster capacity component is configured in a control plane of a cluster including defined custom resource application programming interfaces (APIs) providing at least some of the method functions.

15 . The system of claim 14 , wherein the defined custom resource APIs on each cluster communicate with similar peer defined custom resource APIs on other clusters and the defined custom resource APIs communicate with each other and other components using container orchestration APIs.

16 . A computer program product for container cross-cluster capacity scaling, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
broadcast local capacity information of capacity availability or capacity requirement for the local cluster; receive broadcasts from each of one or more other clusters providing capacity information including capacity availability or capacity requirement; map the received capacity information with the local capacity information; define a time frame for determining i

Assignees

• IBM

Inventors

• Anand Vishal
• Rajaraman Balachandar
• Hay Christopher
• Greig Simon
• Mangla Utpal
• Deshpande Amit

Classifications

• G06F9/541

  via adapters, e.g. between incompatible applications · CPC title

• G06F9/4881

  Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues · CPC title

• G06F2209/505

  Clust · CPC title

• G06F9/5077 Primary

  Logical partitioning of resources; Management or configuration of virtualized resources (specific details on emulation or internal functioning of virtual machines G06F9/455) · CPC title

• G06F9/5088 Primary

  involving task migration · CPC title