Abstract: A method for managing container images in a container hosting environment, comprising a set of machine nodes for hosting container images, comprises the following steps. At a machine node of the set of machine nodes, at least one image layer of a container image comprising multiple image layers is identified for compaction. The identified image layer is compacted by merging data of the identified layer with data of another image layer of the container image. The data of the compacted image layer is transmitted to a backup store remote from the machine node for storage. The set of machine nodes and the backup store are implemented via processing devices operatively coupled via a communication network to form the container hosting environment. The compacted image layer may then be recovered from the backup store.

Abstract: A container is obtained at a host device of a set of host devices in a container hosting environment. At the host device, one or more other host devices of the set of hosting devices are identified as one or more replica host devices. A commit operation is performed at the host device for a given layer of the obtained container. A synchronization operation is then initiated at the host device with each of the one or more replica host devices based on the committed layer of the obtained container to form a replica container at each of the one or more replica host devices. The replica container at each of the one or more replica host devices is state-synchronized with the obtained container.

Abstract: A plurality of data sets to be moved from a source site to a target site in a cloud computing platform is received at a plurality of a containerized data ingest components located at the source site. The received plurality of data sets are provided from the plurality of data ingest components to a staging cluster comprising a plurality of containerized broker components located at the source site, wherein the plurality of containerized broker components queue the plurality of data sets. The queued plurality of data sets are provided from the plurality of containerized broker components to a processing cluster comprising a plurality of containerized data processing components, wherein the plurality of containerized data processing components process the plurality of data sets. The plurality of data sets is transmitted from the plurality of containerized data processing components to the target site.

Abstract: In an information processing system comprising a set of computing devices wherein each computing device comprises a set of persistent memory modules resident in the computing device, a method generates at least one data structure that associates a given application program executing on the set of computing devices with at least one memory region of a given persistent memory module in a given one of the computing devices. The at least one data structure is utilized to route data between the given application program and the at least one memory region.

Abstract: A specification of visualization requirements for a customized visualization associated with one or more storage, compute and networking resources of a data center is generated. Resource data is obtained from one or more data sources, the resource data being associated with one or more of the storage, compute and networking resources of the data center. One or more data views are created utilizing the resource data, each data view comprising a dynamic mapping of the resource data based on the visualization requirements. One or more visuals are rendered utilizing the one or more data views. The customized visualization is generated by organizing the visuals into one or more dashboards of a graphical user interface.

Abstract: Processing nodes in a distributed ad-hoc computing environment are discovered, wherein each processing node is configured to discover other processing nodes. A set of candidate processing nodes is selected from the discovered processing nodes. Selection is based on each discovered processing node advertising its own capabilities to other processing nodes, and processing nodes are selected as candidates based on their advertised capabilities. A subset of processing nodes is formed from the set of candidate processing nodes. The subset of processing nodes forms a self-organized task coordination ensemble wherein each processing node in the task coordination ensemble executes the same consensus protocol. By way of example, the distributed ad-hoc computing environment comprises an IoT network and the processing nodes are IoT devices.

Abstract: A method for processing a data request in a software defined storage system, wherein the software defined storage system comprises one or more nodes configured as a set of client modules operatively coupled to a set of server modules, comprises the following steps. A data request with a data set is received at one of the set of client modules. One or more data services (e.g., deduplication and/or data compression) are performed on the data set, wherein the performance of the one or more data services on the data set is dynamically shared between one or more of the set of client modules and one or more of the set of server modules.

Abstract: Workload data associated with past execution of an application by a computing system is obtained. Two or more prediction models are trained using the obtained past workload data. A weight is assigned to each of the two or more trained prediction models. The two or more weighted prediction models are combined to form an ensemble prediction model configured to predict, in real-time, workload associated with future execution of the application by the computing system.

Abstract: A method, article of manufacture, and apparatus for creating dynamically composed compute nodes from disaggregated hardware components is discussed. These components may be dynamically allocated from resource pools to the compute nodes.

Abstract: A data movement method includes enabling a given data center operatively coupled to one or more other data centers via a communication network to move data between itself and the one or more other data centers in accordance with a peer-to-peer protocol. The given data center and the one or more other data centers thereby form a peer-to-peer network. At least a portion of the given data center and the one or more other data centers are implemented on a cloud computing platform.

Abstract: A method of controlling one or more data services in a computing environment includes the following steps. A request to one of read data from and write data to one or more storage devices in a computing environment is obtained from an application executing on a host device in the computing environment. One or more application-aware parameters associated with the data of the request are obtained. Operation of the one or more data services is controlled based on the one or more application-aware parameters.

Abstract: Techniques are provided for implementing a graphics processing unit (GPU) service platform that is configured to provide topology aware grouping and provisioning of GPU resources for GPU-as-a-Service. A GPU server node receives a service request from a client system for GPU processing services provided by the GPU server node, wherein the GPU server node comprises a plurality of GPU devices. The GPU server node accesses a performance metrics data structure which comprises performance metrics associated with an interconnect topology of the GPU devices and hardware components of the GPU sever node. The GPU server node dynamically forms a group of GPU devices of the GPU server node based on the performance metrics of the accessed data structure, and provisions the dynamically formed group of GPU devices to the client system to handle the service request.

Abstract: A processing device such as a router or other network device implements a locator-identifier mapping system associating identifiers of respective endpoints with respective locators in accordance with a locator-identifier separation protocol. A first one of the endpoints comprises a storage server associated with a storage array. In conjunction with reconfiguration of the storage server, the locator-identifier mapping system updates a particular one of the locators corresponding to the endpoint identifier of the storage server. The reconfiguration of the storage server may comprise, for example, a migration of the storage server within a given data center, or from a first data center to a second data center. The locator of the storage server illustratively specifies a subnet of the storage server. The processing device may comprise a router operating as at least one of an ingress tunnel router and an egress tunnel router in accordance with the locator-identifier separation protocol.

Abstract: A container image registry is maintained at each host device in a set of host devices in a container hosting environment. A container image is composed of one or more container image layers such that each container image registry of each host device is configured to be able to store one or more different layers of one or more different container images. The method tracks which container image registry at which host device contains which container image layers. At each host device, one or more container images are obtained for launching one or more application programs. For a given host device, the one or more container images are obtained from one or more of: (i) one or more container image layers stored in its container image registry; and (ii) one or more container image layers stored in the container image registry of another host device.

Abstract: Example embodiments of the present invention relate to a method, a system, and a computer program product for creating a dynamically composed compute node. The method includes receiving an application characteristic and generating an infrastructure allocation request according to the application characteristic. The infrastructure allocation request then may be forwarded to a management system associated with a disaggregated infrastructure.

Abstract: A system, computer program product, and computer-executable method for managing data I/Os from an application in communication with a cache appliance, wherein the cache appliance is in communication with a cloud storage provider having a first portion of data, the system, computer program product, and computer-executable comprising receiving a data I/O from the application, wherein the data I/O relates to the first portion of data on the cloud storage provider, analyzing the data I/O, creating a caching policy based on the analysis of the data I/O, creating a tenant cache resource vessel based on the caching policy, and managing the data I/O using the tenant cache resource vessel based on the caching policy.

Abstract: A computing platform comprises one or more virtual compute elements, virtual storage elements, and virtual networking elements, wherein one or more application programs of one or more tenants execute on the computing platform. An application program monitoring service layer comprises a set of monitoring service modules selectable by the one or more tenants. The monitoring service modules are configured to provide different application-level monitoring functions, for a given tenant, to monitor the execution of at least one installed application program of the given tenant. A selected monitoring service module executes in at least one virtual compute element that is part of a set of one or more virtual compute elements currently executing the at least one installed application program of the given tenant being monitored. The application program monitoring service layer further comprises a data collecting service module configured to receive application data from the monitoring service module.

Abstract: A method of request scheduling in a computing environment comprises the following steps. One or more requests to at least one of read data from and write data to one or more storage devices in the computing environment are obtained from a host device. The one or more requests are aligned corresponding to a segment size for which one or more data services in the computing environment are configured to process data. The one or more aligned requests are dispatched to the one or more data services prior to sending the one or more requests to the one or more storage devices.

Abstract: A method, a computer program product, a system for analyzing data in a converged infrastructure system, comprising capturing metadata associated with a network path via a port on a network switch enabled to collect metadata; capturing content data associated with the metadata via the port on the network switch enabled to collect metadata; and performing data analytics on the metadata and the content data.

Abstract: A plurality of data sets to be moved from a source site to a target site in a cloud computing platform is received at a plurality of a containerized data ingest components located at the source site. The received plurality of data sets are provided from the plurality of data ingest components to a staging cluster comprising a plurality of containerized broker components located at the source site, wherein the plurality of containerized broker components queue the plurality of data sets. The queued plurality of data sets are provided from the plurality of containerized broker components to a processing cluster comprising a plurality of containerized data processing components, wherein the plurality of containerized data processing components process the plurality of data sets. The plurality of data sets is transmitted from the plurality of containerized data processing components to the target site.