Abstract: A device configured to receive requirements that identifies hardware operating characteristics and to determine a performance metric for the requirements. The device is configured to generate a set of resource cluster configurations that each identify a set of hardware resources and a set of algorithms. The device is further configured to identify a first resource cluster configuration having a first performance value with the highest performance value from among the set of resource cluster configurations. The device is further configured to combine the first resource cluster configuration with a second resource cluster configuration, and to determine a second performance value for the combined resource cluster configuration.

Abstract: A method for deploying a task includes deploying the task in the supercomputer; executing the task; at the end of the execution of the task, detecting at least one link which is not allocated to any task, and setting each detected link in an inactive state, wherein the link requires a power consumption less than the power consumption required by a link associated with at least one task.

Abstract: Described herein are techniques for suspending execution of a process, including through serializing execution state of the process. Through serializing the execution state, the execution state can be converted to a byte string for output. In some embodiments, an executing process that has been suspended may be resumed, through deserializing the execution state. For example, a byte string that is a serialized execution state of a suspended process may be deserialized to generate one or more data objects for the execution state of the suspended process, and a process may be configured with the data objects resulting from the deserializing. By configuring the process with the data objects resulting from the deserializing, the process may take on the execution state of the suspended executing process and resume execution from the point of suspension. The process that may be suspended may be an instance of a request/response application.

Abstract: In one embodiment, a method includes empirically analyzing a set of active reservations and a current set of consumable resources belonging to a class of consumable resources. Each active reservation is of a managed task type and includes a group of one or more tasks requiring access to a consumable resource of the class. The method further includes, based on the empirically analyzing, clocking the set of active reservations each clocking cycle. In addition, the method includes, responsive to the clocking, sorting a priority queue of the set of active reservations.

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to manage a computing resource allocation for a software application. In some implementations, a method may include receiving first metric data associated with the software application, determining, based on the first metric data, that an allocation of a computing resource for the software application is to be reduced from a first level of allocation, increasing allocation of the computing resource to a second level of allocation greater than the first level of allocation; executing the software application on the distributed computing system at the second level of allocation, obtaining second metric data based on execution of the software application at the second level of allocation, and reducing allocation to a third level that is lower than the first level based on a determination that the second metric data does not indicate a performance improvement for the software application.

Abstract: A task manager tightly coupled to a programmable real-time unit (PRU), the task manager configured to: detect a first event; assert, a request to the PRU during a first clock cycle that the PRU perform a second task; receive an acknowledgement of the request from the PRU during the first clock cycle; save a first address in a memory during the first clock cycle of the PRU, the first address corresponding to a first task of the PRU, the first address present in a current program counter of the PRU; load a second address of the memory into a second program counter during the first clock cycle, the second address corresponding to the second task; and load, during a second clock cycle, the second address into the current program counter, wherein the second clock cycle immediately follows the first clock cycle.

Abstract: Systems, devices, media, and methods are presented for throttling (i.e., adjusting) the workload of an application (e.g., number of task requests) in order to improve processor core usage within a heterogeneous multiprocessor system. When high-performance processing is beneficial to the application, the number of task requests may be increased in order to have high-performance processor cores within the heterogeneous multiprocessor system core processor perform the tasks. On the other hand, when high-performance processing is not beneficial, the number of task requests may be decreased in order to have low-performance processor cores within the heterogeneous multiprocessor system perform the tasks. Processor core usage is monitored, and the number of tasks being performed are adjusted to match the processor core usage to a target processor core usage for functions the application is performing.

Abstract: According to one aspect of the present disclosure, a technique for job distribution within a grid environment includes receiving jobs at a submission cluster for distribution of the jobs to one or more execution clusters where each of the execution clusters has one or more execution hosts and maintains a pending job queue. A resource capacity corresponding to each respective execution cluster is determined, and resource requirements for the jobs is determined. A length of the pending job queue indicating a quantity of pending jobs to maintain in the pending job queue for the respective execution cluster is dynamically calculated and periodically adjusted based on the resource capacity and the resource requirements of the respective execution clusters. The jobs are allocated to the respective execution clusters according to the length of the pending job queue of the respective execution clusters.

Abstract: In a computing resource environment including at least one resource capable of being allocated to at least one of a plurality of tasks, techniques are disclosed for applying a taint to a resource in a computing resource environment, the taint being configured to prevent the resource from being claimed for a resource request without a toleration to that taint. Variations include receiving, at a resource scheduler in the resource environment, a request to allocate the resource to perform a particular task and determining whether the resource is subject to a taint. If the resource is subject to a taint, analyzing the request to determine if it includes a toleration for the taint. If the request includes a toleration for the taint, allocating the resource to the task. If the request does not include a toleration for the taint, not allocating the resource due to the taint.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that facilitate efficient allocation of computing resources of a cloud computing environment to job requests. Methods include receiving multiple job requests and sorting these job requests into one or more categories that include job requests with a same or similar set of job attributes. Methods include allocating a first number of computing resources of the compute farm to one or more job requests in each category. Methods include determining an allocation rate at which the first number of computing resources are allocated to the one or more job requests in each category. Methods include determining a remaining number of job requests in each category and allocating a second number of computing resources of the compute farm to the remaining number of job requests in each category based on the allocation rate.

Abstract: An actuator system comprising a shared link arranged to pivot about a first axis relative to a reference structure, a controlled element arranged to pivot about a second axis relative to the reference structure, a first member arranged to pivot about a third axis relative to the shared link and a fourth axis relative to the controlled member, a first actuator arranged to control a first variable distance between the third axis and fourth axis, a second member arranged to pivot about a fifth axis relative to the shared link and a sixth axis relative to the controlled element, a second actuator arranged to control a second variable distance between the fifth axis and the sixth axis, the system configured such that a change in the first variable distance causes rotation of the controlled element about the second axis when the second variable distance is constant and vice versa.

Abstract: A method and an apparatus for migrating a virtual machine across virtualization systems, and a system, where a first virtualization system in which a source virtual machine is located specifies a temporary address of a destination virtual machine. After a second migration tool of a second virtualization system migrates the to-be-migrated virtual machine to the second virtualization system to generate the destination virtual machine, a first migration tool of the first virtualization system controls a migration agent on the destination virtual machine to modify the address of the destination virtual machine to an address of the source virtual machine such that the address of the virtual machine remains unchanged before and after migration, thereby shortening service interruption duration caused by virtual machine migration.

Abstract: The invention relates to a device for optimizing the utilization of the resources on an IT infrastructure (1), the IT infrastructure (1) including one or more IT structures (3) hosting a plurality of application components (2a, 2b, 2c, 2d), said device including a storage module (10) capable of storing a plurality of repositories, a load planning module (20) capable of calculating for a time period required resource levels, an IT structure selection module (30) configured to select IT structures (3) required for the time period and an optimization module (40) configured to generate at least one placement plan including data of IT structures to be used and at least one evolution plan listing resource changes to be made.

Abstract: Systems and methods are provided for assigning and associating resources in a cloud computing environment. Virtual machines in the cloud computing environment can be assigned or associated with pools corresponding to users as dedicated, standby, or preemptible machines. The various states provide users with the ability to reserve a desired level of resources while also allowing the operator of the cloud computing environment to increase resource utilization.

Abstract: In a virtualized environment where multiple guest virtual machines receive security services from multiple security virtual machines, a guest virtual machine automatically transitions to a new virtual security machine under various conditions. For example, the guest virtual machine may select a new security virtual machine when connectivity to the current security virtual machine degrades below a predetermined threshold, or in response to a request from the current security virtual machine indicating, e.g., that the current security virtual machine is about to shut down or otherwise terminate security services to the guest virtual machine.

Abstract: Systems and methods for operating a cloud based computing system. The methods comprise: receiving, by a cloud server, a request for accessing Virtual Hard Disk (“VHD”) data associated with a first location in the VHD of a Virtual Machine (“VM”) hosted by a remote computing device; extracting, by the cloud server, at least a first address specifying the first location from the request; translating, by the cloud server, the first address into a second address specifying a second location in a cloud storage where the VHD data is stored; and communicating from the cloud server the second address to the remote computing device for facilitating access to the VHD data stored in the cloud storage.

Abstract: The disclosure provides an approach for managing an application workload on a computer system that includes data centers. The application workload includes first application instances running on a first data center and second application instances running on a second data center. The method comprises collecting usage data of first application instances, usage data of second application instances, and combining the collected data. The method further comprises evaluating the combined data to determine low health in least one application instance, and restarting the at least one application instance or creating a new application instance. The method further comprises evaluating the combined data to determine whether to change size of the application workload, and in which data center to place a second new application instance if increasing size. The method further comprises contacting a component of the chosen data center to place the second new application instance within a local host machine.

Abstract: Systems and methods are described for managing reuse of sandboxed computing environments in a network-based on-demand code execution system. Users may generate tasks on the system by submitting code to a frontend, which may interact with multiple worker managers that manage task execution in sandboxed computing environments such as containers or virtual machine instances. A sandbox may be reusable once provisioned, but the resources required to definitively locate an idle sandbox may be significant relative to the cost of provisioning a new sandbox. The system may therefore manage reuse by randomly or semi-randomly selecting a worker manager and requesting that it provide an existing sandbox if one is available. If not, then the system may select a different worker manager and repeat the request, or after consuming a threshold amount of resources may request that the next worker manager provision a new sandbox if an existing one is not available.

Abstract: A virtual machine host may provide IPv4 connections to IPv4 virtual machine guests and map the connections to IPv6 networks. The IPv6 addressed exposed by the virtual machine host may be used in an IPv6 environment to communicate with the virtual machine guests, enabling various IPv6 connected scenarios for the IPv4 virtual machines. The virtual machine host may receive IPv6 communications, and translate those communications to IPv4 to communicate with the virtual machine guests. Similarly, the outbound IPv4 communications may be translated into IPv6 for communications to the IPv6 network.

Abstract: Aspects of the disclosure relate to evaluating the rollout of a change to a data processing framework (DPF). A first set of jobs is selected out of a plurality of jobs. The first set of jobs is processed by the DPF with the proposed change enabled and the other jobs of the plurality of jobs by the DPF without the change enabled. A performance cost value is determined for each of the jobs in the first set of jobs processed by the DPF with the proposed change enabled and for each of the other jobs of the plurality of jobs processed by the DPF with the proposed change disabled. Based on the performance cost values of the jobs in the first set of jobs and the performance cost values of the other jobs of the plurality of jobs, a determination is made whether the proposed change is beneficial to the DPF.