Abstract: The disclosure provides an approach for modifying a kernel by adding conditional halting points. The disclosure also provides an approach for modifying a kernel by implementing a virtual shared memory between an application running on a CPU and a workload running on a compute accelerator. The disclosure provides an approach for setting up the kernel and its working set on a compute accelerator, executing the workload, suspending the workload, and then resuming the workload at a later time, optionally on a different host computer.

Abstract: Computational methods and systems that proactively manage usage of computational resources of a distributed computing system are described. A sequence of metric data representing usage of a resource is detrended to obtain a sequence of non-trendy metric data. Stochastic process models, a pulse wave model and a seasonal model of the sequence of non-trendy metric data are computed. When a forecast request is received, a sequence of forecasted metric data is computed over a forecast interval based on the estimated trend and one of the pulse wave or seasonal model that matches the periodicity of the sequence of non-trendy metric data. Alternatively, the sequence of forecasted metric data is computed based on the estimated trend and the stochastic process model with a smallest accumulated residual error. Usage of the resource by virtual objects of the distributed computing system may be adjusted based on the sequence of forecasted metric data.

Abstract: Embodiments for workload management with data access awareness in a computing cluster. In response to receiving an input workload for scheduling by a workload manager, a set of inputs is retrieved from a storage system by a data requirements evaluator module. The data requirements evaluator module generates a list of cluster hosts ranked for performing the input workload according to data access considerations and provides the ranked list of cluster hosts to a scheduler module. The scheduler module generates a scheduling of the input workload to certain hosts within the computing cluster where the generated scheduling is optimized with the data access considerations.

Abstract: Implementations are described for guest controlled virtual device packet filtering. A method of the disclosure includes receiving, at a guest operating system (OS) of a virtual machine executed by a processing device of a host machine, a notification of a host configuration change from a hypervisor of the host machine, the host configuration change affecting routing of networking packets corresponding to the virtual machine over a network, implementing, by the guest OS, configuration changes to a guest OS environment, the configuration changes corresponding to the host configuration change, and in response to implementing the configuration changes, notifying, by the virtual machine, the hypervisor that network packet filtering of the networking packets can be disabled.

Abstract: Methods and systems for migrating a virtual machine instance between devices include one or more migration risk rules, each migration risk rule relating to a validation set having one or more validation substasks. A processor is configured to score a received migration request against one or more of the migration risk rules to generate one or more scores for the migration request, to compare each score to a respective threshold to determine if a level of risk according to the respective rule merits performing validation for the validation set, to validate the migration request by only those validation sets that correspond to the scores that exceed the respective threshold, and to trigger migration of a virtual machine to a target device in accordance with the migration request if none of the validation sets fail to validate the migration request.

Abstract: One embodiment provides a method of identifying discrepancies of an application operating on multiple operating platforms, the method including: utilizing at least one processor to execute computer code that performs the steps of: obtaining a first source code associated with an application of a first operating platform, the first source code including at least one feature of the application; generating, based on the first source code, a first context graph; obtaining a second source code associated with the application of a second operating platform, the second source code including the at least one feature of the application; generating, based on the second source code, a second context graph; comparing the first and second context graph; and identifying, based on the comparison, at least one discrepancy. Other variants and embodiments are broadly contemplated herein.

Abstract: Techniques are disclosed herein for migrating virtual machines. In an embodiment, path configuration information for the source virtual machine is stored within storage allocated to a source virtual machine that is managed by a first hypervisor. A source virtual disk is allocated to the source virtual machine. The source virtual disk includes storage blocks that are accessible by a guest operating system of the source virtual machine. The source virtual disk further includes at least one source management block containing data utilized by the first hypervisor to manage the storage blocks. The guest operating system of the source virtual machine is migrated to a destination virtual machine managed by a second hypervisor. A destination virtual disk is generated that includes the storage blocks that are accessible by the migrated guest operating system.

Abstract: In server/client architectures, the server application and client applications are often developed in different languages and execute in different environments specialized for the different contexts of each application (e.g., low-level, performant, platform-specialized, and stateless instructions on the server, and high-level, flexible, platform-agnostic, and stateful languages on the client) and are often executed on different devices. Convergence of these environments (e.g., server-side JavaScript using Node.js) enables the provision of a server that services client applications executing on the same device. The local server may monitor local events occurring on the device, and may execute one or more server scripts associated with particular local events on behalf of local clients subscribing to the local event (e.g., via a subscription model).

Abstract: A method for discovering an application topology relationship provided by this application, in a packet transmission process, API calling information is recorded, and a topology discovery server determines, by analyzing collected API calling information, whether interaction exists between virtual machines in a virtual machine cluster. By using the foregoing analysis manner, the topology discovery server may further determine interaction frequency that is between virtual machines and to which the collected API calling information relates, and determine an application topology relationship between the virtual machines according to the interaction frequency of the virtual machines.

Abstract: Methods for migrating a virtual machine instance between devices include scoring a received migration request against one or more rules in a rule database to generate one or more scores for the migration request. Each rule relates to one or more respective validation sets. Each score is compared to a respective threshold. The migration request is validated by only those validation sets that correspond to the scores that exceed the respective threshold. A virtual machine is migrated to a target device in accordance with the migration request responsive to successful validation by the validation sets used.

Abstract: Systems and methods for hot-swapping storage pool backend functional modules of a host computer system. An example method may comprise: identifying, by a processing device of a host computer system executing a virtual machine managed by a virtual machine manager, a storage pool backend functional module; and activating the identified storage pool backend functional module by directing, to the identified storage pool backend functional module, backend storage function calls.

Abstract: An RF digitization and collection system (RFDCS) and methods for implementing the RF digitization and collection system to manage an application storage and retrieval space (App Space), wherein the App Space includes apps that may perform various offline and/or real-time transforms of RF signals received, stored, or played back on the RFDCS. Also, in the various embodiments, the RFDCS may govern the system resources available to these apps while ensuring that the RFDCS's core system functions are not impacted by the execution of one or more of these apps in the App Space. Thus, the RFDCS may enable users to utilize real-time signal processing by running various specialized apps without compromising the RFDCS's core system function, thereby promoting dynamic “on-the-fly” transformation of raw RF signals without compromising the user's overall experience.

Abstract: Systems and methods are provided for increasing the likelihood that a set of linked processes related to an application will not be terminated while operating in a background state by substituting a stub process for a main process in the set of linked applications. In response to detecting that the computing device is likely running low on memory, a stub process is created. In some embodiments, the stub process has limited or no functionality and requires less memory than the main process. Process handles of child processes dependent on the main process are transferred to the stub process from the main process. After the transfer, the main process is terminated. In some embodiments, the process may be reversed by transferring process handles for the child process back to the main process and terminating the stub process, such as in response to detecting that the main process has restarted.

Abstract: A parallelization method for generating a parallel program for a multicore microcomputer from multiple processes in a single program for a single-core microcomputer is provided. In the single program, there are multiple types of the processes and a combination of the types of processes to be executed varies according to condition. The parallelization method includes extracting processing patterns respectively representing the combinations of types in the conditions from the single program and allocating the processes to the cores for each of the extracted processing patterns to generate the parallel program.

Abstract: A cloud system data management method for alleviate a data leakage problem occurring when a user accessed by another user when a virtual data volume of the user is mounted to a virtual machine of another user includes creating a first virtual machine for a user and allocating a virtual data volume to the first virtual machine, setting an identifier of the virtual data volume as an identifier corresponding to a home identifier of the first virtual machine, determining, according to the identifier of the virtual data volume and a home identifier of a second virtual machine, whether the virtual data volume and the second virtual machine belong to a same user when the virtual data volume needs to be mounted to the second virtual machine, forbidding the virtual data volume to be mounted to the second virtual machine when they do not belong to the same user.

Abstract: Systems and techniques for memory and resource management in a virtual computing environment are disclosed herein. For example, in some embodiments, an apparatus for memory management in a virtual computing environment may include: a storage device; memory page comparison logic, coupled to the storage device, to determine that a first memory page of instructions, stored in the storage device, for a guest machine in the virtual computing environment is identical to a second memory page of instructions, stored in the storage device, for a host machine in the virtual computing environment, wherein the guest machine is hosted by the host machine; and merge logic, coupled to the memory page comparison logic, to, in response to a determination that the first memory page is identical to the second memory page, map the first memory page to the second memory page. Other embodiments may be disclosed and/or claimed.

Abstract: A method for executing two tasks in timesharing, includes: decomposing offline each task in a repetitive sequence of consecutive frames, and defining a start date and deadline by which an associated atomic operation must respectively start and end; verifying for each frame of a first of the repetitive sequences the corresponding operation can be performed between any two successive operations of a group of frames of the second repetitive sequence, overlapping the first repetitive sequence frame; and if the verification is satisfied, allowing the execution of the two tasks. Scheduling the operations of the two tasks, if two operations can start, executing the operation having the shorter deadline; and if a single operation can start, executing it if its execution need is less than the time remaining until the next frame start date of the other sequence, plus the time margin associated with the next frame of the other sequence.

Abstract: A security system and method efficiently monitors and secures a computer to defend against malicious intrusions, and includes an in-band software monitor disposed within a kernel in communication with an operating system (OS) of the computer. The monitor intercepts system calls made from an MSR (Model Specific Register), to execute monitoring operations, and subsequently returns execution to the OS. An out-of-band hypervisor communicably coupled to the OS, has read shadow means for trapping read requests to the MSR, and write mask means for trapping write requests to the MSR. The hypervisor includes means for responding to the trapped read and write requests so that presence of the monitor is obscured.

Abstract: In a computer-implemented method for calculating a performance metric of a cluster of hosts in a virtualization infrastructure a performance metric of each of a plurality of virtual machines in said virtualization infrastructure is accessing by a centralized management application of a virtualization infrastructure. The virtualization infrastructure comprises a plurality of hosts supporting the plurality of virtual machines. A performance metric of a cluster of the plurality of hosts is calculated by the centralized management application based on the performance metric of each of the plurality of virtual machines hosted by the cluster. The calculated performance metric of the cluster is transmitted to a database such that a history of performance metrics of the cluster are stored in the database.

Abstract: A thread in a computing system is processed for execution of instructions to perform an action. The action is one of the following: accessing a shared resource or executing a critical section of code. A schedule of the thread is managed. The management prevents suspension of the thread during execution of the action.