International Business Machines Corporation

Xun Pan

Peng Li

Hai Hui Wang

Xiang Zhen Gan

Guang Ya Liu

Zhaohui Ding

Rong Song Shen

Xiu Qiao Li

Xin Peng Liu

Xiao Liang Hu

Jing Chen

Guang Han Sui

Shan Gao

Lei Gao

Jing Zhang

A Peng Zhang

Na Liu

Jin Wang

Michael Spriggs

Yuanyuan He

Guangya Liu

Dan Sun

Zi Yun Kang

Ge Wei Pang

Wen Qing Jin

Chun Lin Yang

Chao Deng

Yu Dong Wang

Disclosed is an approach for image management for container runtimes. A first image of a first application for a first container runtime can be downloaded from an image repository providing the first image. Content data of the first application and management data corresponding to the first application and the first container runtime can be extracted from the first image. Both the content data of the first application and the management data corresponding to the first application and the first container runtime can be stored in an image sharing file system in response to the content data of the first application being not stored in the image sharing file system. Only the management data corresponding to the first application and the first container runtime can be stored in the image sharing file system in response to the content data of the first application being stored in the image sharing file system.

Image management for container runtimes

In a job management environment comprising a plurality of job systems and a scheduler for scheduling a job submitted to the job management environment to a job system for running, a processor, in a first job system, intercepts, from outside of a first container in the first job system, a first job from being sent to the scheduler. A processor, in the first job system, determines whether the first job is submitted from a container in the first job system. In response to a first determination that the first job is submitted from a container in the first job system, a processor, in the first job system, determines contexts of the first job, the contexts of the first job including a context related to the first container. A processor, in the first job system, sends the first job together with the contexts of the first job to the scheduler.

Propagating job contexts to a job execution environment

Methods, computer program products, and/or systems are provided that perform the following operations: identifying, in an environment that includes a plurality of edge clusters of edge nodes, a first edge cluster having a resource gap; broadcasting a resource requirement of the first edge cluster to other edge clusters in the plurality; obtaining resource commitments from one or more of the other edge clusters; selecting edge cluster resources from the one or more of the other edge clusters based, at least in part, on the resource commitments; and creating a new cluster including the first edge cluster and the selected edge cluster resources.

Dynamic clustering of edge cluster resources

Provisioning an orchestration platform is provided. A pre-application programming interface (API) server hook is used to preprocess a request to generate a custom resource in the orchestration platform. The pre-API server hook generates a custom resource definition corresponding to the custom resource and generates the custom resource based on the custom resource definition. A custom resource definition generation event is monitored for, using a custom resource definition (CRD) meta-controller, to manage a custom resource definition controller corresponding to the custom resource definition. The CRD meta-controller retrieves the custom resource definition controller from a CRD controller configuration repository to deploy the custom resource definition controller on a worker node in the orchestration platform. Data is distributed, using a data partition proxy, to the custom resource definition controller running the custom resource on the worker node to ensure that no overlapping of data processing tasks exists in the orchestration platform.

Event-driven provisioning of an elastic orchestration platform

Computer technology for protecting data security in a computerized system for recommending content to users where, a processing unit generates an identifier for a first data record relating to a user device based on a first machine learning model. Then, the processing unit sends the identifier to a service provider, and the service provider uses the identifier to determine one or more contents to be sent to the user device. Creating and using a decision tree machine learning (ML) model and a cluster ML model with training records and a transformed records.

Data protection in network environments

Methods, computer program products, and/or systems are provided that perform the following operations: identifying a first workload being processed by a first plurality of sites in a cluster; identifying, from the first plurality of sites: (i) a first site as a primary site for the first workload, and (ii) one or more secondary sites for the first workload; identifying a communication link issue between the first site and at least one of the one or more secondary sites; splitting the cluster into sub-clusters based, at least in part, on the communication link issue, wherein the first site is included in a first sub-cluster of the sub-clusters and the at least one of the one or more secondary sites is included in a sub-cluster of the sub-clusters that is different from the first sub-cluster; and instructing the first sub-cluster to locally process the first workload.

Auto-split and auto-merge clusters

A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations. The operations may include registering a custom resource definition for a tenant with a host and scaling a controller for the customer resource definition. The operations may include generating a replication using the customer resource definition, injecting information into the replication, and syncing a status of the custom resource definition between the host and the tenant.

Extend controller for multi-tenancy

A computer-implemented method, an apparatus, and a computer program product for edge node autonomy. For a first edge node of a plurality of edge nodes in a federation in a distributed computing framework, one or more processors receive a request to be sent to a central node in the distributed computing framework. The one or more processors determine whether the federation is connected to the central node. In response to determining that the federation is not connected to the central node, the one or more processors determine whether a controller capable of processing the request is available in the federation. In response to determining that the controller capable of processing the request is available in the federation, the one or more processors notify the controller to process the request.

Edge node autonomy

A processor may receive a composable deployer comma-separated values (CSV) file. The processor may parse the composable deployer CSV file. The processor may determine if there is a composable deployer foundation template. The processor may install a resource. The resource to install may be associated with the composable deployer foundation template.

Composable deployer architecture

A computer-implemented method, a computer system and a computer program product for releasable resource-based preemptive scheduling. One or more currently running workloads are determined to be preempted by a pending workload. Releasable resources from the one or more currently running workloads meet required resources of the pending workload. The pending workload is dispatched so that it uses at least part of the releasable resources from the one or more currently running workloads to run.

Releasable resource based preemptive scheduling

A method and system for process tracking is disclosed. A first process is associated with an identity of a job, wherein the first process is launched by an outsourcing process to process the job. A second process is created locally. The second process is associated with the identity of the job to enable the second process to manage the first process based on the identity.

Growing community of inventors

Xi'an, China

Xun Pan