International Business Machines Corporation

Lukas Rupprecht

Vasily Tarasov

Constantine Arnold

Deepavali M Bhagwat

Dimitrios Skourtis

Rui Zhang

Wayne A Sawdon

Subashini Balachandran

Gregory Tad Kishi

Tanveer Fathima Syeda-Mahmood

Joseph W Dain

Nimrod Megiddo

Renu Tewari

Hongzhi Wang

Chao Zheng

James C Davis

Nitin Ramchandani

A computer-implemented method according to one embodiment includes receiving a request to create a container; retrieving a manifest for a container image of the container; and mounting a file system for the container, utilizing the manifest.

Container image creation and deployment using a manifest

A computer-implemented method according to one embodiment includes receiving a manifest for a container image of a container to be created; identifying a mapping index for a cluster of computing nodes; and selecting a computing node within the cluster of computing nodes to create the container, based on a comparison of the manifest to the mapping index.

Content-aware node selection for container creation

A dataset formatted in a first format is generated, wherein the dataset formatted in the first format includes at least a plurality of data elements that comprise data. A selection is made of machine learning framework, wherein the machine learning framework operates on datasets formatted in a second format that is different from the first format. The dataset is converted from the first format to the second format and links are generated from the converted dataset formatted in the second format to the plurality of data elements of the dataset formatted in the first format to avoid creating additional copies of the plurality of data elements.

Generation of a dataset in the format of a machine learning framework

A computer-implemented method according to one embodiment includes monitoring for occurrence of trigger events corresponding to creation of metadata in a computing environment, and detecting occurrence of a trigger event. The method further includes loading a rule that is associated with the detected trigger event in response to detecting occurrence of the trigger event. The rule includes a condition and an action, and the action defines a subset of metadata associated with processing a job in the computing environment. The method further includes collecting the defined subset of metadata in accordance with the action in response to the condition of the rule being met, and storing the collected subset of metadata. A system according to another embodiment includes a processor, and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor. The logic is configured to perform the foregoing method.

Rule-based collections of subset(s) of metadata in response to a trigger event occurring

A computer-implemented method includes receiving characteristic information of a container registry. The container registry includes a plurality of container images. The method includes selecting at least two container images in the container registry and selecting parameters for optimization based on the characteristic information. The method also includes generating a cost function based on the parameters for optimization and optimizing the at least two container images in the container registry based on the cost function. A computer-implemented method includes receiving a composition of each of at least two layers in a container image. The composition of each of the at least two layers includes at least one file. The method includes mapping overlap between the composition of the at least two layers and estimating a redundancy in the container image based on the overlap. The method also includes calculating new layers which reduce the redundancy in the container image.

Optimizing image reconstruction for container registries

A mechanism is provided in a data processing system to implement a data mapping engine for transparent and declarative translation of search queries on documents to queries on relational data. The data mapping engine receives a query from a search framework for a target database and translates the query to a target schema based on a mapping definition data structure to form a translated query. The mapping definition data structure declaratively maps between a source schema of the search framework to a target schema of a target database. The data mapping engine sends the translated query to the target database and receives a response from the target database. The data mapping engine translates the response to the source schema based on the mapping definition data structure to form a translated response and sends the translated response to the search framework.

Mapping document data to relational data

According to one embodiment, a computer program product for managing contention includes a computer readable storage medium that has program instructions embodied therewith, where the computer readable storage medium is not a transitory signal per se, and where the program instructions are executable by a processor to cause the processor to perform a method including incrementing, by the processor, a counter associated with an image in response to a creation of a container instance using the image, comparing, by the processor, the counter to a threshold value, and conditionally replicating the image by the processor, based on the comparing.

Sharing container images utilizing a shared storage system

In an approach to optimizing container images through automatic layer suggestions, one or more computer processors identify one or more layers contained within an image. The one or more computer processors compare each identified layer with one or more layers contained in an image repository. The one or more computer processors calculate a layer overlap score for each compared layer. The one or more computer processors determine a potential substitute layer utilizing a respective calculated layer overlap score. The one or more computer processors, responsive to the determined substitute layer exceeding a layer overlap score threshold, substitute one or more identified layers with the determined substitute layer. The one or more computer processors restructure one or more layers of the image based on the substituted layer.

Container optimization through automatic layer suggestions

A computer-implemented method according to one embodiment includes monitoring and storing historical data access to image data by a container within a container environment, identifying or predicting that a container is to be started utilizing the image within the container environment, predicting data to be accessed by the container, based on the historical data access by the image, and initiating a copy-on-write (COW) for the data to be accessed by the container, in response to identifying or predicting that the container is to be started.

Performing proactive copy-on-write for containers

Various embodiments are provided for managing memory for image analysis in a computing environment by a processor. An estimated amount of memory may be reserved for an image analysis job. During a processing of the image analysis job, at least one thread of the image analysis job is partially suspended by restricting the image analysis job from requesting allocation of additional memory upon memory requirements for the image analysis job exceeding the estimated amount of memory. Commensurate with partially suspending the at least one thread, a state of the image analysis job is maintained in the memory notwithstanding the processing of the at least one thread associated with the state is suspended.

Memory management for complex image analysis

A computer-implemented method according to one embodiment includes identifying an event within a system; applying a model to the event to create an aggregated event; and storing the aggregated event.

Performing hierarchical provenance collection

A computer-implemented method according to one embodiment includes identifying an input/output (I/O) operation to be implemented within a distributed computing environment, where the distributed computing environment executes a plurality of different jobs, determining information associated with the I/O operation indicating that the I/O operation is associated with a recovery of one of the plurality of different jobs, and assigning an implementation priority to the I/O operation, based on the information associated with the I/O operation.

Growing community of inventors

San Jose, CA, United States of America

Lukas Rupprecht