Abstract: The technology disclosed herein identifying a workflow file in a storage location associated with a trigger event responsive to detecting the trigger event, generating, using the identified workflow file, a new specification definition, storing, in a temporary service registry, the new specification definition, wherein the new specification definition is one of a plurality of temporary specification definitions in the temporary service registry, and identifying from the list of specification definitions the one or more specification definitions based on a parameter of a request responsive to receiving the request for one or more specification definitions of a list of specification definitions. The list of specification definitions including the plurality of temporary specification definitions in the temporary service registry and a plurality of predefined specification definitions in a remote service registry.

Abstract: There is provided a device for allocation of memory configured for: in response to a request for allocation of a region of a pool of a memory by a process being executed by a processor, a memory allocator is configured to perform in a single atomic operation: read a data structure indicating a state of allocation of the pool, check the data structure for a condition, update the data structure according to an outcome of the check, and return an address of the allocated region of the memory.

Abstract: A system for accelerator functions as a service is disclosed. The system may receive a job that includes a computer (CPU) portion and an accelerator portion. When the accelerator portion is performed, an execution time associated with a time for the accelerator to return results is determined. Resources or a portion thereof allocated to the job, or the CPU portion are freed or reallocated to another job at least during the execution time. The job is queued to receive resources when the results are received from the accelerator.

Abstract: Disclosed systems and methods align virtual machines (VMs) with hyperconverged infrastructure (HCI)-based hardware based on a determination of the VM's characteristic type. Each cluster node may be provisioned with a specific combination of hardware. In some embodiments, disclosed methods include determining, for each of the plurality of nodes, a target workload type based at least in part on the combination of information handling resources provisioned on each node. Disclosed methods may manage deployment of the VMs among the cluster nodes based on one or more factors including a workload compatibility factor determined in accordance with a workload type of each VM and a target workload type of each node, where the target workload type may reflect a hardware characteristic of the node.

Abstract: Systems and methods for generating runtime predictions in distributed computer architectures are disclosed. According to one embodiment, a method for generating runtime predictions in a distributed computer architectures may include: (1) receiving, by a runtime prediction computer program executed by an electronic device, training data regarding completion of a plurality of risk compute jobs; (2) extracting, by the runtime prediction computer program, bucketing statistics and instrument level features from the data; (3) training, by the runtime prediction computer program, a machine learning model with the training data, the extracted bucketing statistics, and the instrument level features; (4) receiving, by the runtime prediction computer program, a plurality of jobs for a period of time; and (5) calculating, by the runtime prediction computer program, an instrument cost for each of the jobs using the machine learning model.

Abstract: Processing methods is provided. A method is designated as schedulable. A completion stage is generated for the method. A return of the completion stage corresponding to the method is received. It is determined whether a state of the completion stage indicates continued execution of the method. In response to determining that the state of the completion stage does indicate continued execution of the method, a set of executions of the method is continued based on an execution return of the method being a null return.

Abstract: A shutdown criterion is determined to be met with respect to a cluster. Responsive to determining that the shutdown criterion is met, a request router is configured to route requests addressed to the cluster to a destination that indicates that the cluster is unavailable. A request to shut down the cluster is transmitted. A request to start the cluster is received. The request is initiated via the destination that indicates that the cluster is unavailable. In response to receiving the request to start the cluster, the cluster is started and the request router is configured to direct, to the cluster, requests addressed to the cluster.

Abstract: Systems and methods for estimating the scalability of applications in high performance computing and distributed computing environments and for configuring applications based on those estimates are disclosed. A model is disclosed that provides an estimate of the scalability behavior of an application based on basic parameters and a small number of runs on bare metal and cloud systems. The system may also be configured to use the estimated performance to recommend optimal configurations based on different policies, including best performance, lowest cost, and best performance per cost.

Abstract: A virtual machine memory management method and device are provided. The method includes: identifying memory of a non-operating system of a virtual machine from total memory allocated to the virtual machine, where the total memory includes memory of the virtual machine and management memory of a hypervisor, and the memory of the virtual machine includes memory of an operating system of the virtual machine and the memory of the non-operating system of the virtual machine; using the memory of the non-operating system of the virtual machine as swappable memory; and storing data in the swappable memory into a nonvolatile memory. This method helps avoid a problem that computer performance significantly deteriorates in a virtual machine over-submission scenario, and improve stability in running of a virtual machine and users' use experience.

Abstract: A method and an apparatus of creating a container, an electronic device, and a storage medium. The method includes: acquiring an available rack list and an available network address list, the available rack list including a plurality of available racks of different available zones, each available rack including at least one server node, the available network address list including at least one available network address; locating a spare server node in the available racks in the available rack list; creating, on the spare server node, a current container corresponding to the available network address; updating the available network address list; re-ordering the available racks in the available rack list according to resource occupation information of the available racks in the available rack list; and creating another container according to a spare server node in the re-ordered available racks in the available rack list and the updated available network address list.

Abstract: An agent task scheduler may include a local timer to generate a current local timer value. An agent task scheduler, independent of other agent task schedulers, may arrange to periodically perform a task scheduling process. The agent task scheduler may obtain a current Domain Name System (“DNS”) text record that includes a next timer value indicating when a task should next be executed and a prior timer value indicating when the task was last executed. If the current local timer value is greater than the next timer value in the DNS text record, the scheduler may update the next timer value in the DNS text record to the current local timer value plus a value associated with periodic performance of the task scheduling process. The scheduler may also update the prior timer value in the DNS text record to the current local timer value and perform the task.

Abstract: System and method for running virtual machines within containers. An example method may include: running, by a host computer system, a hypervisor managing a first virtual machine implemented by a first container with a first set of resources, creating, by the hypervisor, a second container implementing the second virtual machine, wherein the second container is nested within the first container, determining, by the first virtual machine of the first container, one or more of the first set of resources to assign to the second container, and assigning, by the hypervisor, to the second container one or more of the first set of resources.

Abstract: A method comprises receiving a request to predict an amount of at least one resource for at least one hosting instance of one or more microservices. Using one or more machine learning models, the amount of the at least one resource is predicted in response to the request. The at least one hosting instance is generated based, at least in part, on the predicted amount. In some embodiments, the at least one resource comprises, for example, a memory and/or a CPU, and the amount of the at least one resource comprises a size of the memory and/or a number of CPU core units.

Abstract: Techniques are provided for managing load distribution in a data storage system which comprises storage server nodes and storage nodes, wherein each storage server node comprises one or more distribution targets, wherein each distribution target comprises a logical processing unit that is configured to manage input/output operations for accessing data in the storage nodes. A process for managing the load distribution comprises: partitioning a logical address space into a plurality of distribution items; mapping the logical address space to a sequence of one or more distribution templates, wherein each distribution template comprises an ordered list of the distribution targets of the storage server nodes, which is uniquely different for each of the one or more distribution templates; and utilizing the one or more distribution templates to map the distribution items of the logical address space to the distribution targets of the storage server nodes.

Abstract: A method, computer program product and computer system to calculate resource quotas in a distributed computing environment are provided. A processor retrieves workload data regarding a plurality of workloads in a shared computing environment, where the plurality of workloads are executing or pending execution within the shared computing environment. A processor identifies a plurality of tenants of the shared computing environment associated with the plurality of workloads. A processor determines an expected resource usage for the plurality of tenants. A processor determines a ratio of resource usage for the plurality of tenants. A processor determines a resource limit for the plurality of tenants. A processor adjusts at least one aspect of the shared computing environment based on a determination that a total expected resource usage for both executing and pending workloads of a tenant exceeds a resource limit associated with the tenant.

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: Aspects include monitoring, by a controller, an operational status of a tracker system that is configured to track and record a current status of a job being executed and to report completion of the job to the controller. The recording includes storing two copies of the current status, where a first copy is stored in a shared memory location accessible by the controller. In response to determining, based on the monitoring, that the tracker system is operational, waiting to receive a job completion message for the job from the tracker system and performing a job completion action based on receiving the job completion message. In response to determining that the tracker system is not operational, obtaining the current status of the job from the shared memory location and performing the job completion action based on the current status indicating that the job has completed.

Abstract: Techniques are provided for semantic-aware workflow creation and execution. One method comprises obtaining a semantic-aware workflow; identifying objects specified in the semantic-aware workflow; performing, for at least one of the identified objects: extracting parameters corresponding to the at least one identified object using an attribute registry associated with the semantic-aware workflow; selecting, using the attribute registry, an extracted parameter that takes, as a value, another identified object; and adding an operation to the semantic-aware workflow using the at least one identified object, and the corresponding selected extracted parameter that takes, as a value, the other identified object.

Abstract: In various embodiments, a resource allocation management circuit may allocate a plurality of different types of hardware resources (e.g., different types of registers) to a plurality of threads. The different types of hardware resources may correspond to a plurality of hardware resource allocation circuits. The resource allocation management circuit may track allocation of the hardware resources to the threads using state identification values of the threads. In response to determining that fewer than a respective requested number of one or more types of the hardware resources are available, the resource allocation management circuit may identify one or more threads for deallocation. As a result, the hardware resource allocation system may allocate hardware resources to threads more efficiently (e.g.

Abstract: Examples described herein relate to a centralized workflow management system (CWMS) and a method for managing the deployment and migration of virtual computing instances along a manufacturing line. The manufacturing line hosts a plurality of computing devices such as a first computing device and a second computing device to control operations performed by respective machines. To manufacture a first product, a first orchestration manager hosted in the CWMS deploys a first virtualized computing instance on the first computing device associated with a first stage of a first product manufacturing workflow. Further, upon the first product completing the first stage of the first product manufacturing workflow, the first orchestration manager migrates the first virtualized computing instance from the first computing device to a second computing device associated with a second stage of the first product manufacturing workflow.