Abstract: Method, computer program product, and computer system are provided. Traffic is collected against a NoSQL database by an activity collector. A database transaction log is periodically extracted and analyzed. The collected traffic and the analyzed database transaction log are input to building a knowledge base of database access patterns. Current traffic is captured and used to compute an activity threshold. Traffic is directed to a workload processor based on the activity threshold. Traffic is directed to an intensive insert/update/delete (IUD) processor in response to the activity threshold exceeding a configured threshold. A plurality of temporary shards is generated along with an adaptive key and adaptive index in the plurality of temporary shards. The intensive IUD processor traffic is re-directed to the plurality of temporary shards while the activity threshold exceeds the configured threshold.

Abstract: A computer implemented method, apparatus, system, and computer program product manages updates to images. A computer system determines shared layers present between the images selected for update management. The images comprise executable code that are run to create containers. The computer system detects a change in a shared layer in the shared layers for an image in the images. The computer system updates the shared layer in the shared layers in a set of the images having the shared layer in response to detecting the change to the shared layer for the image. According to other illustrative embodiments, a computer system and a computer program product for managing updates to images are provided.

Abstract: A present invention embodiment requests resources for a set of tasks from different resource providers. The set of tasks includes first tasks and second tasks of longer duration than the first tasks. The resources are revocable by the different resource providers based on processing demand. Performance of the first tasks is initiated on the resources, and stable resources are identified based on revocation of the resources during performance of the first tasks. Performance of the second tasks are initiated on the identified stable resources. Requests for the resources to the different resource providers are adjusted based on resource provider information collected in response to completion of the set of tasks.

Abstract: Method, computer program product, and computer system are provided. Traffic is collected against a NoSQL database by an activity collector. A database transaction log is periodically extracted and analyzed. The collected traffic and the analyzed database transaction log are input to building a knowledge base of database access patterns. Current traffic is captured and used to compute an activity threshold. Traffic is directed to a workload processor based on the activity threshold. Traffic is directed to an intensive insert/update/delete (IUD) processor in response to the activity threshold exceeding a configured threshold. A plurality of temporary shards is generated along with an adaptive key and adaptive index in the plurality of temporary shards. The intensive IUD processor traffic is re-directed to the plurality of temporary shards while the activity threshold exceeds the configured threshold.

Abstract: File system performance enhancement is provided. Information related to a container of the computer accessing a file in a layer of a file system of an image corresponding to the container is recorded to form recorded file system layer access information. The recorded file system layer access information is shared with another file system of a container image corresponding to a different container on the computer. The container image is a same image as the image corresponding to the container that accessed the file to perform an operation associated with a cloud application.

Abstract: This disclosure provides a method, a computing system and a computer program product for managing resource sharing among devices with different platforms. The method comprises obtaining connection information for connecting to a requesting device by decoding authentication information, wherein the authentication information is created based at least on an identifier of the requesting device. The method further comprises sending a request including the connection information to a request proxy, wherein the request is redirected by the request proxy to a plurality of devices having more than one platform. The method further comprises receiving a response to the request, wherein the response is obtained by combining responses received by the request proxy from the plurality of devices.

Abstract: Embodiments of the present disclosure relate to a method, system and computer program product for providing system services. In some embodiments, a method is disclosed. According to the method, from a user program in a user address space, a request for a system service is received via a program call instruction of a set of program call instructions in an application interface code library. Based on the program call instruction, a target authorized address space of a plurality of authorized address spaces and a target system service routine for providing the system service in the target authorized address space is determined. A result of running the target system service routine in the target authorized address space is returned to the user program as a response to the request.

Abstract: In an approach to building a file system for multiple architectures, responsive to receiving a manifest for a file system build, a base layer is retrieved for each platform to be built, where the base layer is an operating system base. Responsive to determining that any layer to be built has not been built, the next layer to be built is retrieved. Responsive to the next layer to be built is platform-independent, the next layer is retrieved from a cache, where the next layer supports each platform. Responsive to the next layer to be built is platform-dependent, the next layer is built, where a copy of the next layer is built for each platform. The above steps are iteratively repeated until each layer is built. A single image of a completed file system build is stored, where the single image supports each platform.

Abstract: A block of data intended for a set of receiving computer systems comprising a first system and a second system is divided into a set of equal-size portions. A first portion of the set of portions is transmitted from a first file server storing the block of data to the first system. The first portion is relayed from the first file server to a second file server concurrently with the transmitting. The first portion of the set of portions is transmitted from the second file server to the second system.

Abstract: In an approach for building file server arrays with stable and unstable nodes for enhanced pipeline transmission, a processor builds an array from a plurality of stable nodes, wherein each stable node of the plurality of stable nodes is linked to two other stable nodes of the plurality of stable nodes forming a line. A processor divides a plurality of unstable nodes into one or more groups of unstable nodes. A processor links each group of unstable nodes to two neighboring stable nodes within the array. A processor sends data through the array and the one or more groups of unstable nodes in two opposite directions. A processor monitors a node status for each node of the plurality of stable nodes and the plurality of unstable nodes.

Abstract: Creating a storage driver that is structured and configured to organize and operate a multiple layer file system on a cloud-based computing server, and more particularly to a containerized computing server. Additionally, the storage driver is used to improve the security of the containers and to define a static configuration of the multiple layer file system that is stored within the containers.

Abstract: An approach for intelligent task message queue management may be provided herein. The approach may include receiving a task message from a producer at an intelligent task message queue management service. The approach may include assigning a subclass to the task message based on a predetermined set of rules. The approach may include assigning the task message to a one of a plurality of subclass worklist queues based on the assigned subclass. The approach may include generating a subclass score for the task message based on a weight associated with the assigned subclass work queue. The approach may include dispatching the task message to a consumer based on the generated subclass score for the task message.

Abstract: A method, a computer program product, and a computer system run an inference model with a graphical processing unit (GPU) having a restrained resource. The method includes receiving an input to run a sequential inference process comprising a plurality of layers. The method comprises determining inference model information. The method comprises determining a count (M) of the layers for each step to load and run based on the inference model information. The method comprises determining allocations in the available GPU memory configured for data associated with the M layers, a step input and a step output, and intermediate information. The method comprises loading and running the M layers using the step input to calculate the step output. The method comprises generating the intermediate information for the step output for a subsequent step to utilize the step output as a further step input in the subsequent step.

Abstract: A thread management process where a storage area template is generated for a plurality of threads that are to be created by a process in a computing system, the storage area template comprising at least one module template for at least one library that is to be loaded by the process. In the computing system, a plurality of storage areas is allocated for the plurality of threads based on the storage area template, respectively. The plurality of threads are managed based on the plurality of storage areas, respectively. All threads and libraries may be managed in a uniform way according to the storage area template. Therefore, thread management may be simplified and then may lead to reduced costs in the storage and time resources.

Abstract: Solutions preparing container images and data for container workloads prior to start times of workloads predicted through workload trend analysis. Local storage space on the node is managed based on workload trends, optimizing local storage of image files without requiring frequent reloading and/or deletion of image files, avoiding network intensive I/O operations when pulling images to local storage by workload scheduling systems. Systems perform collection of historical data including image and workload properties; analyze historical data for workload trends, including predicted start times, image files needed, number of nodes and types of nodes. Based on predicted future workload start times, nodes are selected from an ordered list of node requirements and workload properties.

Abstract: A computer implemented method controls in a core dimension packing the plurality of processing unit cores to reduce partial use of the plurality of processing unit cores by concurrently loading into the plurality of processing unit cores: all computational nodes of at least one member selected from the group consisting of the first number of whole groups and the first number of partial groups; and all computation nodes of at least one member selected from the group consisting of the second number of whole groups and the second number of partial groups. According to other illustrative embodiments, a computer system and a computer program product for packing the plurality of processing cores are provided. As a result, the illustrative embodiments can provide a technical effect of increasing the performance in running jobs in a computer system in which partial use of processing unit cores can be reduced.

Abstract: A first memory page in a memory of the computer is allocated as a first stack to buffer meta data for function calls in the program. A memory protection key for the first memory page is generated. A second memory page in the memory is allocated as a second stack to buffer user data for function calls in the program.

Abstract: A computer-implemented method includes receiving, by a computing system, an update for a computer program executing on the computing system. The method further includes determining, by the computing system, a data structure that is affected by the update by checking a structure change information included in the update. The method further includes checking, by the computing system, instance-count of the data structure, the instance-count representing a number of instances of the data structure in a memory of the computing system. The method further includes based on a determination that the instance-count is zero, applying, by the computing system, the update to the computer program.

Abstract: A computer-implemented method comprises initializing a plurality of segment lists. Each segment list of the plurality of segment lists corresponds to a respective one of a plurality of disk drives. Each segment list divides storage space of the respective disk drive into a plurality of segments. The method further comprises, for each of the plurality of disk drives, identifying one or more candidate segments from the plurality of segments; calculating a respective segment distance variance for one or more combinations of identified candidate segments. Each combination of identified candidate segments includes one candidate segment for each of the plurality of disk drives. The method further comprises selecting a combination of the one or more combinations of identified candidate segments having the smallest respective segment distance variance; and storing data on the plurality of disk drives according to the selected combination of identified candidate segments.

Abstract: The present invention relates to a method, system and computer program product for task failover in an unstable environment, wherein the unstable environment includes a plurality of reclaimable nodes. According to the method, it is monitored if any node of the plurality of reclaimable nodes is to be reclaimed. Whether a task on any node of the plurality of reclaimable nodes is recoverable is determined. Responsive to the task being recoverable, data of the recoverable task is stored. Responsive to a node being reclaimed and the task on the reclaimed node being recoverable, at least one associated task of at least one associated node of the reclaimed node is notified to wait.