Abstract: Processing a transaction is disclosed including receiving a global transaction start request sent by a message sending terminal, the global transaction start request instructing that a message link-level transaction be started, assigning a unique transaction identifier to the message link-level transaction, and sending a global transaction ID to the message sending terminal, the global transaction ID including the unique transaction ID and an address of a transaction coordinator configured to coordinate the message link-level transaction.

Abstract: Balancing a recurring task between multiple worker processes is disclosed. Each of a plurality of worker processes attempt, over a period of time, to acquire a task lock. A first worker process of the plurality of worker processes acquires the task lock. The first worker process performs a task that is associated with the task lock and sets a timer for an amount of time that prevents acquisition of the task lock by any other worker process for the amount of time.

Abstract: Real-time job distribution software architectures for high bandwidth, hybrid processor computation systems for semiconductor inspection and metrology are disclosed. The imaging processing computer architecture can be scalable by changing the number of CPUs and GPUs to meet computing needs. The architecture is defined using a master node and one or more worker nodes to run image processing jobs in parallel for maximum throughput. The master node can receive input image data from a semiconductor wafer or reticle. Jobs based on the input image data are distributed to one of the worker nodes. Each worker node can include at least one CPU and at least one GPU. The image processing job can contain multiple tasks, and each of the tasks can be assigned to one of the CPU or GPU in the worker node using a worker job manager to process the image.

Abstract: Described herein are systems and methods that manage machine backups, including the creation of virtual machine packages sufficient to instantiate virtual machines corresponding to the backups. In one aspect, a compute infrastructure includes many machines, which may be either physical or virtual. From time to time, snapshots of the states of these target machines are pulled and saved. Virtual machine packages corresponding to these snapshots are also created. A virtual machine package can be used to instantiate a virtual machine (VM) emulating the target machine with the saved state on a destination virtual machine platform. At some point, the initial VM package for a target machine is created by converting the snapshot to a VM package. However, this may take a long time. Later VM packages can instead be created by updating a prior VM package according to differences between the corresponding snapshots, rather than performing the full conversion process.

Abstract: An apparatus and a computer program product include program instructions configured to be executable by a processor to cause the processor to perform operations. The operations include managing workload instances running on a computing system that includes a plurality of compute nodes, wherein the workload instances include at least one workload instance owned by each of a plurality of users. The operations further include identifying, for each workload instance, which user among the plurality of users owns the workload instance and which compute node among the plurality of compute nodes is running the workload instance. Additionally, the operations further include enabling, for any given compute node among the plurality of compute nodes, a particular user among the plurality of users to perform a management function on the given compute node in response to all of the workloads running on the given compute node being owned by the particular user.

Abstract: Systems and methods for batching operations in a virtualization environment. A method embodiment operates over a plurality of virtual machines in the virtualization environment. A user interface is used to select two or more virtual machines that are to be subjected to the same batch actions. A method step then generates at least one batch request to be performed over the two or more selected virtual machines. In forming the batch request, the states of the individual virtual machines are analyzed to determine one or more entity-specific operations that apply to the virtual machines and/or to constituent entities of the virtual machines. Once the state-specific and entity-specific operations have been determined, an entity management protocol initiates execution of the one or more entity-specific operations over the individual ones of the two or more selected virtual machines.

Abstract: Methods and systems for allocating disk space and other limited resources (e.g., network bandwidth) for a cluster of data storage nodes using distributed semaphores with atomic updates are described. The distributed semaphores may be built on top of a distributed key-value store and used to reserve disk space, global disk streams for writing data to disks, and per node network bandwidth settings. A distributed semaphore comprising two or more semaphores that are accessed with different keys may be used to reduce contention and allow a globally accessible semaphore to scale as the number of data storage nodes within the cluster increases over time. In some cases, the number of semaphores within the distributed semaphore may be dynamically adjusted over time and may be set based on the total amount of disk space within the cluster and/or the number of contention fails that have occurred to the distributed semaphore.

Abstract: A virtualization management/orchestration apparatus is provided with: a Network Function Virtualization Orchestrator (NFVO) that reads a Network Service Descriptor (NSD) in which an entry defining dependency between a VNF and a prescribed element is provided, and creates the VNF and the prescribed element according to the dependency defined in the NSD; and/or a VNF manager (VNFM) that reads a Virtualized Network Function Descriptor (VNFD) provided with an entry defining dependency between a VM and a prescribed element, and creates the VM and the prescribed element according to the dependency defined in the VNFD.

Abstract: A system for virtual machine live migration includes a management node, a source server, a destination server, a peripheral component interconnect express (PCIe) switch, and an single root input/output virtualization (SR-IOV) network adapter, where the source server includes a virtual machine (VM) before live migration; the destination server includes a VM after live migration; the management node is adapted to configure, using the PCIe switch, a connection relationship between a virtual function (VF) module used by the VM before live migration and the source server as a connection relationship between the VF module and the destination server; and the destination server, using the PCIe switch and according to the connection relationship with the VF module configured by the management node, uses the VF module to complete virtual machine live migration. By switching the connection relationships, the system ensures that a data packet receiving and sending service is not interrupted.

Abstract: Technology is disclosed for establishing and administering multiple virtual machines, each with an audio, video and control (AVC) operating system (OS). The technology can also establish and administer cloud based AVC OSs. A server implementing this technology can perform real-time AVC processing, alongside soft and non-real-time processing and can host multiple, independent, virtual AVC OSs. Each AVC OS can perform the processing for an AVC setup. Each of the AVC OSs can be operated by a corresponding virtual machine controlled by a hypervisor running on the server. A cloud based AVC OS can perform processing for a corresponding remote AVC setup comprising multiple AVC devices. An AVC routing system can cause AVC signals from a particular AVC setup to reach a corresponding cloud AVC OS and conversely can cause signals from an AVC OS to reach the correct destination device.

Abstract: According to an example, a computer creates an application entry in a social application page, receives a triggering operation command associated with the application entry, generates, based on the triggering operation command, a floating layer at a predetermined position on the social application page, receives application data at the floating layer, and runs an application in the floating layer based on the application data.

Abstract: A method is provided for a protection module or a process to use a hypervisor to protect memory pages of a guest operating system on the hypervisor. The method includes modifying a shared memory page in a context of the process, which causes the guest operating system to allocate a private memory page to the process, copy data from the shared memory page to the private memory page, and modify the private memory page. The method further includes causing the hypervisor to protect the private memory page by monitoring the private memory page and generating an alert when the private memory page is accessed.

Abstract: Embodiments of the present invention disclose a method, computer program product, and system for processing a thread of execution on a plurality of independent processing cores. In various embodiments, a run state and a local maximum thermal power is assigned to each of at least part of the cores. A first one of the cores is set to the active state. The thread on the first core in the active state is processed. The processing of the thread on the first core for fulfilment of an interrupt condition is monitored. A second one of the cores is set to the active state. The processing of the thread on the first core is halted. The processing of the thread to the second core is transferred. The processing of the thread on the second core in the active state continues and the first core is set to the cooling state.

Abstract: A plurality of interfaces that share a plurality of resources in a storage controller are maintained. In response to an occurrence of a predetermined number of operations associated with an interface of the plurality of interfaces, an input is provided on a plurality of attributes of the storage controller to a machine learning module. In response to receiving the input, the machine learning module generates an output value corresponding to a number of resources of the plurality of resources to allocate to the interface in the storage controller.

Abstract: A machine learning module receives inputs comprising attributes of a storage controller, wherein the attributes affect allocation of a plurality of resources to a plurality of interfaces. In response to a predetermined number of I/O operations occurring in the storage controller, a generation is made via forward propagation through a plurality of layers of the machine learning module, of an output value corresponding to a number of resources to allocate to an interface. A margin of error is calculated based on comparing the generated output value to an expected output value that is generated from an indication of a predetermined function based at least on a number of I/O operations that are waiting for a resource and a number of available resources. An adjustment is made of weights of links that interconnect nodes of the plurality of layers via back propagation, to reduce the margin of error.

Abstract: Systems and methods for scheduling, within a virtual machine, central processing unit time to be reserved for host machine execution of tasks are described. An example method may include execution, by a hypervisor running on a host computer system, a virtual machine comprising a virtual central processing unit. The virtual central processing unit is associated with a physical central processing unit of the host machine. The hypervisor determines a portion of central processing unit time to be reserved for host execution. The hypervisor notifies the virtual machine of the portion of central processing unit time that is reserved for host execution.

Abstract: Techniques for implementing 3DI API redirection for VDI desktops are provided. In one set of embodiments, a server system can intercept a call to a 3D API made by a 3D application running within a VM on the server system, where the VM hosts a desktop that is presented to a user of a client system. The server system can determine metadata associated with the call, where the metadata including a name of the 3D API and one or more input parameter values to the call, and can transmit the metadata to the client system. In response, the client system can reconstruct the call to the 3D API using the metadata and execute the call using one or more physical GPUs residing on the client system.

Abstract: A synchronization process for virtual-machine images (and other segmented files) provides for generating a “delta” bitmap indicating which segments (e.g., clusters) of a first virtual-machine image were changed to obtain a second (e.g., updated) virtual-machine image on a source node. The delta bitmap can be applied to the second-virtual-machine image to generate a delta file. The delta file can be sent along with the delta bitmap to a target node that already has a copy of the first virtual-machine image. The transferred delta bitmap and delta file can then be used on the target node to generate a replica of the second virtual-machine image, thereby effecting synchronization. In variations, different bitmaps and delta files can be transferred to optimize the synchronization process.

Abstract: A multi-processor system includes multiple processors arranged in multiple clusters. Different clusters have different power and performance characteristics. The system includes a task scheduler to schedule tasks to the processors. The task scheduler, in response to detection of a scheduling event trigger, is operative to identify a scheduling objective between a first objective of energy optimization and a second objective of load balance. The scheduling objective is identified based on at least respective operating frequencies and loading of all processors in a highest-capacity cluster of the multiple clusters. According to the identified scheduling objective, the task scheduler schedules a given task to a processor selected among the processors in the multiple clusters.

Abstract: A method, an information handling system (IHS), and a host group generating system for collecting information about host groups in a cluster of IHSs using a management controller. The method includes retrieving, from a controller memory, first target physical hosts that are part of a virtual machine manager (VMM) host group, but not on a VMM host list and retrieving second target physical hosts that are part of the VMM host list, but not part of the VMM host group. The method further includes transmitting, to each of the first target physical hosts, a request to detach from the VMM host group. The method further includes transmitting, to each of the second target physical hosts, a request to attach to the VMM host group.