Abstract: An exemplary system includes first and second controllers each configured to selectively operate in a master state and a standby state, a first watchdog timer associated with the first controller, and a second watchdog timer associated with the second controller. Each watchdog timer is configured to be either unexpired or expired. Selectively, the first controller operates in the master state and the second controller operates in the standby state when the first watchdog timer is unexpired and the second watchdog timer is expired, the first controller operates in the standby state and the second controller operates in the master state when the first watchdog timer is expired and the second watchdog timer is unexpired, and the first and second controllers both operate in the standby state when both the first and the second watchdog timer are expired or when both the first and the second watchdog timer are unexpired.

Abstract: A method by a computing system implementing a node within a cluster of nodes to load balance among the cluster of nodes using retroactive refusal. Each of the nodes within the cluster of nodes is capable of processing work items. The method includes accepting a work item to be processed by the node, monitoring a resource utilization of the node, determining whether the resource utilization of the node exceeds a predetermined threshold, and retroactively refusing the work item in response to a determination that the resource utilization of the node exceeds the predetermined threshold, wherein the retroactive refusal causes the work item to be reassigned from the node to another node within the cluster of nodes.

Abstract: The present disclosure involves systems, software, and computer implemented methods for resource allocation and management. One example method includes receiving, in a dispatching layer, a request to run a first task for a first application, the request including a first application priority. At least one second application priority of at least one currently running application is identified. A maximum number of allowable parallel tasks per application is determined. Application priority weights are assigned to each of the first application priority and the at least one second application priority. A number of parallel tasks for the first application and the at least one currently running application are determined based on the maximum number of allowable parallel tasks per application and the assigned application priority weights. A first number of parallel tasks are assigned to the first application. The first application is executed using the assigned first number of parallel tasks.

Abstract: Embodiments include method, systems and computer program products for executing one or more composite templates to provision composite service instances. The method includes provisioning, by one or more processors, one or more instances of one or more composite templates. The one or more processors further provision one or more instances of template members associated with each of the one or more composite templates. The one or more processors further receive a selection of one or more actions to be performed on the one or more instances of the one or more composite templates or one or more template members. The one or more processors further execute the selected one or more actions.

Abstract: A system and method are provided for facilitating configuration of one or more references to a software service to be called by a software application. A catalog process is provided. The catalog includes information identifying services to be called to implement processes. Service references occurring in a process template are determined that are used to implement the processes identified in the catalog. During a build phase, a tokenized process template is created by replacing each of the service references in the process template with a respective token. At least one of the processes is run in accordance with the tokenized process template, including resolving the tokens and invoking at least one service identified thereby.

Abstract: Systems and methods for high availability cloud service provision are disclosed. A server receives, from a remote device, a request to access a specified service, the specified service being associated with a plurality of virtual machines, each of the plurality of virtual machines storing shared states associated with the specified service. The server provides, to the remote device in response to the request, a connection to a first virtual machine of the plurality of virtual machines and identifiers of other ones of the plurality of virtual machines. The server determines to end a data connection the remote device and the first virtual machine while continuing to provide the specified service to the remote device. The server provides, to the remote device in response to determining to disconnect the remote device from the first virtual machine, a connection to a second virtual machine of the plurality of virtual machines.

Abstract: A computer-implemented method includes: monitoring, by a computing device, computing resource utilization by a plurality of virtual computing components sharing a same kernel; monitoring, by the computing device, transaction counts produced by the plurality of virtual computing components; determining, by the computing device, that the transaction counts increase by less than a threshold number as the computing resource utilization increases; and creating, by the computing device, an additional virtual computing component on a separate kernel based on determining that the transaction counts increase by less than a threshold number as the computing resource utilization increases.

Abstract: A method and an apparatus to execute a code compiled from a source code to access an untyped variable are described. An optimized access code may be compiled in the code with speculative optimization via a type prediction of runtime value of the untyped variable. Invalidity of the type prediction may be dynamically detected for future runtime values of the untyped variable. The code may be updated with an access code compiled for the access without the speculative optimization based on the invalidity detection. The updated code can be executed for the access to the untyped variable without executing the optimized access code.

Abstract: A lock control apparatus includes one or more memories, and one or more processors configured to perform setting of, as a target node, each of one or more child nodes other than eldest child nodes among child nodes relating to parent nodes in each of layers of data structure formed by a tree structure, when a first process for first data associated with a first node in the data structure proceeds in a direction from a parent node to a child node, perform determination of whether the first node is the target node, and perform lock of the first node when the first node is the target node.

Abstract: Embodiments are directed to a computer implemented method of controlling a host computing device connected to at least one subordinate computing device. The method includes configuring a host virtual machine manager (VMM) of the host computing device to perform a method that includes deploying an instance of a subordinate virtual machine (VM) on the subordinate computing device, and deploying another instance of the subordinate VM on the host computing device. The method further includes administering features or functions of the instance of the subordinate VM on the subordinate computing device, and administering features or functions of the another instance of the subordinate VM on the host computing device.

Abstract: Embodiments for optimizing memory placement in a disaggregated computing environment. A new workload is assigned to a subset of a plurality of processors, the subset of processors assigned a subset of a plurality of memory devices. In some embodiments, a determination is made as to whether the new workload is categorized as a memory-dependent workload having a memory need which can be met primarily by the subset of the memory devices. If the new workload is categorized as a memory-dependent workload, a determination is then made as to whether the subset of the memory devices is meeting the memory need of the new workload. When the subset of the memory devices is not meeting the memory need of the new workload, a memory related action is taken.

Abstract: According to one embodiment, an electronic apparatus includes a nonvolatile memory and a hardware processor. The nonvolatile memory is configured not to permit a user using the electronic apparatus to access the nonvolatile memory. The hardware processor is configured to download a client program for connection to a first server apparatus configured to provide a virtual desktop environment, from a second server apparatus different from the first server apparatus, make the downloaded client program stored in the nonvolatile memory, and launch the client program stored in the nonvolatile memory in order for the electronic apparatus to receive the virtual desktop environment, in a case where the client program is stored in the nonvolatile memory.

Abstract: Systems and methods are provided to implement intelligent data coordination for accelerated computing in a distributed computing environment. For example, a method includes executing a task on a computing node, monitoring requests issued by the executing task, intercepting requests issued by the executing task which correspond to data flow operations to be performed as part of the task execution, and asynchronously executing the intercepted requests at scheduled times to coordinate data flow between resources on the computing node.

Abstract: A method for provisioning a computer includes providing a graph that defines relationships between one or more hardware components of a plurality of computers and component characteristics of the one or more hardware components, and relationships between one or more applications and requirements of the one or more applications. The method further includes receiving a selection of an application and determining, via the graph, whether at least one computer with hardware components capable of meeting the requirements of the application exists. If a computer exits, the method also includes communicating the application to the computer; triggering the computer to execute the application; and communicating, from the computer, data processed by the application to an external system.

Abstract: Prioritizing resource allocation to computer applications which includes: grouping the computer applications into groups according to an initial criteria; modifying the groups according to one or more criteria used to identify active computer applications; analyzing the groups to prioritize the groups in order of the active time of the computer applications in the groups; analyzing the computer applications in the groups to prioritize the computer applications in the groups in order of the active time of the computer applications in the groups; setting the highest priority for the computer applications that either (1) have high frequency of use, or (1) are active now; and prioritizing the computer applications according to the priority setting.

Abstract: The disclosed technology relates to cloud computing and, more specifically, to a cloud computing platform that manages cloud infrastructure to provide autonomous management of containers hosting applications. Based on prediction computations, the disclosed technology can scale up a VM or container, scale down a VM or container, shutdown a VM or container, change the location of a container, open a new container, or close a container.

Abstract: Techniques for centralized management of network switch operations across multiple virtualization platforms via a “spanned distributed virtual switch.” These techniques generally include creating a distributed virtual switch for each virtual platform that participates in the spanned distributed virtual switch, configuring each such distributed virtual switch with a mutually exclusive set of ports, configuring each distributed virtual switch with network configuration information for associated sets of ports, and synchronizing the network configuration information across distributed virtual switches. When configuration information changes in one distributed virtual switch, those changes are synchronized across other distributed virtual switches that participate in the spanned distributed virtual switch. A computer system, method, and computer-readable medium are provided herein.

Abstract: A computer system, method, and computer readable product are provided for event-based serverless computing with tiered latency. In various embodiments, computer-executable instructions are received along with an indication of an event whose occurrence triggers execution of those instructions within a container on a serverless computing platform. Additionally, the instructions come with an indication of an acceptable amount of latency between the event occurring and the instructions being executed. Multiple different actions may be made to execute the instructions based on that indicated latency.

Abstract: A system for adjusting oversubscription loading includes an interface and a processor. The interface is configured to receive a set of performance data from a set of worker systems. The processor is configured to determine a feedback indication for a worker system of the set of worker systems based at least in part on the set of performance data. The feedback indication is used to adjust an oversubscription controller on the worker system. The processor is configured to provide the feedback indication to the worker system.

Abstract: Placement of instances of virtual machine (VM) images in a cloud computing environment is optimized. A request is received to deploy a new VM image instance. VM resource usage profiles are read that indicate predicted resource consumption data of the VM image. Resource pool profiles for multiple resource pools are read that indicate predicted resource consumption data for the resource pools. For each of the resource pools, the VM resource usage profile is aligned with the respective resource pool profile. An aggregated resource consumption profile is calculated as an aggregation of the predicted resource consumptions of the aligned profiles. A determination is made of one of multiple resource pools with the least predicted aggregated resource consumption, and the VM image is instantiated on the determined one of the multiple resource pools with the least predicted aggregated resource consumption over time.