91results about "Resource allocation" patented technology

The system and method for structuring self-provisioning workloads deployed in virtualized data centers described herein may provide a scalable architecture that can inject intelligence and embed policies into managed workloads to provision and tune resources allocated to the managed workloads, thereby enhancing workload portability across various cloud and virtualized data centers. In particular, the self-provisioning workloads may have a packaged software stack that includes resource utilization instrumentation to collect utilization metrics from physical resources that a virtualization host allocates to the workload, a resource management policy engine to communicate with the virtualization host to effect tuning the physical resources allocated to the workload, and a mapping that the resource management policy engine references to request tuning the physical resources allocated to the workload from a management domain associated with the virtualization host.

An execution management method includes providing an execution plan, balancing an execution load across a plurality of servers, automatically interpreting the execution plan, and re-driving a failed test to another of the plurality of servers if the test case fails on an originally selected available server. The execution plan includes a plurality of test cases and criteria corresponding to the test cases. More than one of the plurality of test cases may be run on each of the plurality of servers at a same time in parallel. Each of the plurality of servers is run independently.

Hypervisor managed memory paging is provided in a data processing system having multiple logical partitions. The data processing system includes a shared memory pool defined within physical memory. The shared memory pool includes a volume of physical memory with dynamically adjustable sub-volumes or sets of physical pages associated with the multiple logical partitions. Each sub-volume or set is associated with a particular logical partition and includes mapped logical memory pages for that logical partition. A hypervisor memory manager interfaces the multiple logical partitions and the shared memory pool, and manages access to logical memory pages within the shared memory pool. The hypervisor memory manager further manages page-out and page-in of logical memory pages from the shared memory pool to one or more external paging devices. This page-out and page-in managing by the hypervisor memory manager is transparent to the multiple logical partitions.

A method, apparatus, and computer program product for using a multi-core integrated circuit having cores with differing performance characteristics. The cores are arranged into high and low performance groups and tasks are assigned according to their priority to either a high or low performance group.

The invention discloses a batch data processing method and device, computer equipment and a storage medium. The batch data processing method comprises the steps: selecting a target batch task from a non-real-time task queue, and creating a data processing queue based on the target batch task; determining target idle information from the target idle time queue, obtaining the number of to-be-processed data corresponding to the to-be-processed data, obtaining the target number based on the number of the to-be-processed data, the target idle duration and the estimated thread number, selecting theto-be-processed data corresponding to the target number from the data processing queue, and determining the to-be-processed data as segmentation processing data; when the original load of the system is smaller than a busy load threshold value, obtaining a target processing thread, adopting the target processing thread to perform data processing on the segmentation processing data in the target idle duration, and obtaining a data processing result; and based on the data processing result, updating the task state of each split processing data in the data processing queue. According to the batchdata processing method, system resources can be reasonably distributed, and the batch data processing efficiency is ensured.

An adaptive scheduling host system of GPU (Graphics Processing Unit) virtual resources in a cloud game comprises a scheduling control module, as well as an agent module, an image application programming interface analysis module and a virtual machine list which are connected with the scheduling control module respectively, wherein the agent module consists of a scheduling module and a monitoring module; all the modules are allocated in a host; the scheduling control module is responsible for information communication among the other modules; and the scheduling control module obtains information of all running virtual machines from the virtual machine list and transmits the information to the requiring module. The system realizes scientific management of the GPU resources in the virtual machines, and increases the utilization ratio of the GPU resources, the enough GPU resources are distributed to all the running virtual machines based on a fair QoS (Quality of Service) adaptive scheduling method in a fair distribution manner, the QoS requirements are met, and the utilization ratio of a whole GPU is maximized.

An infrastructure for providing cloud services is described. In particular embodiments, a cloud infrastructure system, including one or more computing devices, performs a method for processing a subscription order for one or more services provided to a customer by the cloud infrastructure system. The method includes storing a subscription order information related to a subscription order received from a customer for one or more services provided by the cloud infrastructure system. The method includes identifying a process associated to be used for servicing the subscription order. The process comprises one or more execution steps for provisioning one or more resources for the one or more services identified in the subscription order. The method includes orchestrating the performance of the one or more execution steps corresponding to the process. The cloud infrastructure system sends a notification to a customer indicating a status of the subscription order.

A collection/distribution server divides processing task accepted from a customer terminal into a plurality of processing units, and transmits the units to at least one or more user terminals. The collection/distribution server receives processing results of execution on the user terminals, and integrates the processing results to send back to the customer terminal.

The user terminal registers with an application server in advance for receiving a task commission from the collection/distribution server, and receives a license application from the application server. When the license application receives a processing unit from the collection/distribution server, the license application executes the processing on the user terminal. The license application sends back a result of the processing to the collection/distribution server via a network. The user terminal receives a specified service as good value for executing the processing task substituting for a contractor.

The invention discloses a task adjusting method for embedded type software and a device thereof. The method comprises steps as followed: S1, a high priority adjusting task is created, S2, the adjusting task receives registration information of an adjusted task, wherein the registration information at least comprises detecting cycle and high threshold value of CPU occupancy, S3, the adjusting task obtains the running status of the adjusted task according to the detecting cycle, and if the CPU occupancy of the adjusted task is higher than the high threshold value of CPU occupancy, then the adjusted task is released for a certain time. The invention utilizes a high priority adjusting task to count the running states of each task at real time, when the CPU occupancy of the adjusted task is higher than the set high threshold value of CPU occupancy, the adjusted task can be released for a while by the adjusting task, thereby guaranteeing system normal operation, and increasing system reliability.

The present invention provides generalized database tables to implement the classifications of Resource Type, Resource Specification, and Resource Instance, supplemented by individual tables specific to each type of resource, and by the associations and dependencies between them. More specifically, this invention provides database tables comprising a group of structures including Resource Type, Resource Specification and Resource Instance. The Resource Instance is a representation of an individual computing resource, each Resource Instance relates to a physical or logical instance of one Resource Specification. A Resource Specification is a collection of features and functions of a given resource, belonging to one Resource Type which can have zero, one or more resource instances associated with it. A Resource Type, being the highest level of the Resource Model can have zero, one or many resource specifications associated with it.

A computer system includes a plurality of clusters each having at least one resource. At least one cluster has a resource matched with static resource information of a cluster discovery request. The at least one cluster is selected by referring to static resource information of resources in each cluster of a discovery object. The at least one cluster is a candidate cluster. A resource matched with dynamic resource information of a resource discovery request is searched from the candidate cluster by referring to dynamic resource information of resources in the candidate cluster.

The invention discloses a system and method for providing cryptographic service through a virtual cryptographic equipment cluster. The system is composed of a cloud cryptographic service interface, a task scheduler, multiple cryptographic machines, and a state detector. The method provided by the invention comprises the following steps: (1) detecting load information of each cryptographic machine; (2) computing a commercial cryptographic algorithm occupancy rate of each cryptographic machine; (3) computing a load value of each cryptographic machine; (4) ordering the load values; (5) initiating a service request; (6) processing the service request; (7) selecting the cryptographic machine; (8) judging whether the working state of each cryptographic machine is normal; (9) processing a service request and responding; (11) receiving a service response; (12) feeding back the load information; (13) judging whether the cryptographic service request is finished; and (14) finishing the cryptographic service. By use of the system and method disclosed by the invention, the virtual cryptographic equipment cluster can be satisfied so as to provide the actual demand of the cryptographic operation service.

The invention provides a data center energy consumption scheduling method and a data center energy consumption scheduling device. The method comprises the following steps of acquiring resource utilization rate and/or environment temperature of one or a plurality of cabinets of a data center; and scheduling energy consumption of the data center according to the acquired resource utilization rate and/or the environment temperature. By the data center energy consumption scheduling method and the data center energy consumption scheduling device, the problems that reduction treatment on the energy consumption of a data center is incomplete by using a correlation technique and the energy using efficiency of the data center is not high are solved, energy consumption scheduling of load distribution can be realized, and energy consumption of refrigeration equipment of the data center is reduced to a certain degree.

The invention provides a local dynamic migration method and control system based on a Docker container technology, and belongs to the technical field of cloud computing. The problem of resource wastein an existing container migration technology is solved. The method determines the appearing of an overload server and triggers container migration according to the node resource usage rate and the predicted resource usage rate in the last n sampling periods; for the selection of a to-be-migrated container in the overload server, a container with large total usage rate and smaller internal storageis selected firstly to achieve the effect of balancing load while reducing migration overhead. For the selection of a target server, firstly enough available resources in the target server are ensured. For the case where a new container is generated in the migration process and the target server is overloaded caused by paralleling, it means that there is no server which can accommodate the container in all servers in the cluster, so that there is no need to migrate the container and replace the to-be-migrated container. The local dynamic migration method and control system improve resource utilization and reduce task execution time.

A task scheduling method and apparatus are provided. The task scheduling method comprise steps of acquiring current task information including a task type, acquiring resource information of a client matching the task type, selecting a target client according to the resource information and distributing the current task to the target client. Scheduling efficiency can be improved by the use of the task scheduling method and apparatus.

The invention describes techniques for managing resources at a wireless device. In one aspect, the wireless device controls applications based on resource demands and available resources. Processing demands by the applications may be monitored, and at least one of the applications may be controlled based on the processing demands and a maximum processing capacity of a processing unit executing the applications. A data application may be controlled by reducing the amount of data exchanged by the application when high processing demands are detected, and vice versa. In another aspect, the wireless device varies resource capacity to match resources demands. The processing capacity of the processing unit may be adjusted based on the processing demands. Higher clock frequency may be selected for the processing unit when the processing demands exceed a high threshold, and lower clock frequency may be selected when processing demands fall below a low threshold.

An apparatus is disclosed for allocating processing resources, such as instruction execution which can be measured in MIPs or memory capacity, or other resources of a processor itself or resources used in the process of performing operations, such as memory resources, busses, drivers and the like, to functions in a queue waiting to be executed. This apparatus includes a capacity determining device for determining an amount of the processor resource available to be assigned, a load determining device for determining an estimate of an amount of the resource needed for each function waiting in the queue to execute, a prioritization device for prioritizing each of the functions in the queue waiting to be executed, and an allocating device, which receives information from the capacity determining device, the load determining device, and the prioritization device, for allocating the available resource to the functions based on a hierarchical priority scheme.

Method, system, and programs for dynamic control of a processing system having a plurality of tiers. Queue lengths of a plurality of nodes in one of the plurality of tiers are received. A control objective is received from a higher tier. One or more requests from the higher tier are processed by the plurality of nodes in the tier. A control model of the tier is computed based on the received queue lengths. One or more parameters of the control model are adjusted based on the received control objective. At least one control action is determined based on the control model and the control objective.

Embodiments described herein provide a system for facilitating efficient benchmarking of a piece of hardware for artificial intelligence (AI) models. During operation, the system determines a set of AI models that are representative of applications that run on the piece of hardware. The piece of hardware can be configured to process AI-related operations. The system can determine workloads of the set of AI models based on layer information associated with a respective layer of a respective AI model in the set of AI models and form a set of workload clusters from the determined workloads. The system then determines, based on the set of workload clusters, a synthetic AI model configured to generate a workload that represents statistical properties of the determined workload.

A method of configuring a logical network in a datacenter is provided. The datacenter includes a plurality of host physical computing devices, a compute manager to configure one or more data compute nodes (DCNs) on virtualization software of each host, and a network manager. The method configures, by the network manager, a logical network. the method provides, by the network manager, a read-only configuration construct of the logical network to the virtualization software of a set of hosts in the plurality of hosts. The method obtains, by the compute manager, the read-only configuration construct of the logical network from the virtualization software of the set of hosts. The method configures, by the compute manager, a plurality of DCNs to connect to the logical network using the read only configuration construct of the logical network.

The embodiment of the invention discloses a business processing method, comprising: obtaining the first reliability parameter of a node device; receiving the second reliability parameter and the third reliability parameter sent by the node device; calculating the reliability estimation value of the node device according to the first reliability parameter, the second reliability parameter and the third reliability parameter, wherein the reliability estimation value is used for determining the deploying position of an object business; deploying the object business on at least one node device according to the reliability estimation value so that at least one node device executes the object business. The embodiment of the invention also provides an arrangement device, the node device and a system. The embodiment of the invention can take more factors into consideration and is not limited to a traditional mode; the third reliability parameter is added to participate in reliability estimation of the node device, thus ensuring the accuracy of deploying the business on a virtual machine.

The invention relates to a virtualization management system for logic CPE equipment based on a Docker technology and a configuration method thereof. The system comprises a first Docker container, a second Docker container, a third Docker container and a fourth Docker container, separately corresponding to a DP level, a CP level, an MP level and a DP-manager on which the logic CPE equipment are deployed, and correspondingly applied to virtualization management of the DP level, the CP level, the MP level and the DP-manager on which the logic CPE equipment are deployed. According to the Docket container technology, isolation between the logic CPE equipment logic levels is achieved, the customized characteristic requirements of different users are met via the multiple pieces of logic CPE equipment based on the Docker container technology, and the problem that the virtualization equipment is large in resource consumption and low in forwarding efficiency is solved via the physical single instance and logic multi-instance of the DP level.