Abstract: Disclosed methods, systems, and apparatus, include computer programs encoded on computer storage media, for performing allocation of M resources among N users into K pools by solving a knapsack problem (KP) using a distributed computing system. The method includes: receiving data representing K global constraints and L local constraints of the KP; transforming the KP into a dual problem using K dual multipliers; decomposing the dual problem into N sub-problems; performing two or more iterations in solving the dual problem, wherein in one iteration, for each dual multiplier corresponding to a global constraint corresponding to a pool: determining an updated dual multiplier for the global constraint corresponding to the pool to be a non-negative threshold; and computing M decision variables of each of the N users corresponding to the updated dual multiplier in solving each of the N sub-problems corresponding to the each of the N users.

Abstract: The topology and operation of virtual entities and sub-entities of a data center may be monitored and correlated to services and customers supported by the data center.

Abstract: A self-adjusting resource-provisioning system that infers the existence of extrinsic events by monitoring external information sources. When an external source satisfies a threshold condition, the system, as a function of historical records, correlates the inferred event with a likelihood that a Web site or other computerized entity's resource-utilization will reach a certain level at a future time. The system adjusts the available amount of resources to handle the predicted utilization level. If the system fails to accurately predict the actual utilization level, the system adjusts the condition to more accurately predict utilization in the future. If no threshold condition predicts an unexpected change in resource utilization, the system adjusts parameters of an existing condition or creates a new condition to better correlate utilization with future extrinsic events.

Abstract: Systems and methods for enabling a hypervisor to more efficiently determine the instruction executed by the virtual machine that causes a transition event. An example method may comprise: determining, by a processing device executing a hypervisor, a data storage location of a particular instruction of a guest operating system; detecting, by the hypervisor, a transition event between a virtual machine executing the guest operating system and the hypervisor, wherein the virtual machine comprises a virtual processor; comparing, by the hypervisor, an instruction pointer of the virtual processor and the data storage location of the particular instruction to determine a cause of the transition event; and executing, by the hypervisor, an operation corresponding to the cause of the transition event.

Abstract: Disclosed is a method for controlling a database service for processing a service according to an exemplary embodiment of the present disclosure.

Abstract: Techniques for providing high-performance buffer caches for transactional input/output (I/O) systems are disclosed. The techniques include obtaining a first logical creation time of a resource to be acquired by the first transaction during a pre-commit phase of a first transaction with an I/O system. When the first logical creation time exceeds a latest logical creation time from a set of resources previously acquired by the first transaction, the first logical creation time of the resource is compared with an earliest logical termination time from the set of resources. When the first logical creation time of the resource exceeds the earliest logical termination time from the set of resources, a conflict between the resource and the set of resources is detected, and a restart of the first transaction is triggered.

Abstract: Embodiments perform capability discovery, policy management, and policy enforcement to provide data in-flight (DIF) services to virtual machines (VMs) without requiring modification to established storage protocols. In exemplary embodiments, a management device receives advertisements of DIF services supported by network nodes. The management device groups the advertised DIF services into a DIF services policy. The management device associates a host and a communication path. The management device enforces the DIF services policy by storing a unique number that causes transmission of data along the communication path.

Abstract: A mechanism is provided for a cloud computing infrastructure, a mechanism is provided for balancing client sessions across virtual machines such that the number of virtual machines is efficiently managed. In some embodiments, the total number of virtual machines is minimized to reduce power consumption, cooling, and other cost drivers, while assigning users across the sessions. In one embodiment, the sessions in a virtual machine with low activity are migrated to a virtual machine with higher session rates to allow for the shutdown of the low usage virtual machines. In another embodiment, new user sessions are assigned according to a minimum performance standard.

Abstract: A computer processing system includes at least one processor to operate based on an operating system, and to detect when a user session is opened. The computer processing system includes a workspace environment management engine to manage a workspace environment of the computer processing system in response to detecting when the user session is opened. The workspace environment management engine identifies if an engine configuration repository of tasks and settings to be performed include a new task or setting that is not in a saved configuration repository. If a new task or setting has been identified, then the workspace environment management engine performs the new task or setting for the workspace environment.

Abstract: Examples described herein include distributed computing systems having a system traffic analyzer. The system traffic analyzer may receive sampled packets sent to a network from a number virtual machines hosted by computing nodes in the distributed computing system. The packets may be sampled, for example, by network flow monitors in hypervisors of the computing nodes. The system traffic analyzer may request co-location of virtual machines having greater than a threshold amount of traffic between them. The request for co-location may result in the requested virtual machines being hosted on a same computing node, which may in some examples conserve network bandwidth.

Abstract: A method for automatic application deployment, and a cloud management node, where the method includes receiving an application orchestration template input by a user, parsing out an application model characteristic of an application from the application orchestration template, determining, according to the application model characteristic and a preset rule, a first instance creation manner corresponding to the application, determining a first computer device corresponding to the first instance creation manner in multiple computer devices, and sending a first instance creation command to the first computer device, the first instance creation command instructing the first computer device to create a first instance for the application according to the first instance creation manner. Therefore, application can be efficiently deployed automatically.

Abstract: A system and method include initiating a live migration of a virtual machine from a first host machine to a second host machine. A shared host physical storage includes first swapped out memory data associated with the first virtual machine from a first memory of the first host machine, and metadata including location information of the first swapped out memory data, and an identity of the associated first virtual machine. The system and method include copying memory data associated with the first virtual machine stored in the first memory to the second host machine. The system and method also include accessing, by a second hypervisor at the second host machine, the metadata stored in the shared host physical storage to determine location of the first swapped out memory data associated with the first virtual machine.

Abstract: A central processing unit (CPU) forming part of a computing device, initiates execution of code associated with each of a plurality of objects used by a worker thread. The CPU has an associated cache that is split into a plurality of slices. It is determined, by a cache slice allocation algorithm for each object, whether any of the slices will be exclusive to or shared by the object. Thereafter, for each object, any slices determined to be exclusive to the object are activated such that the object exclusively uses such slices and any slices determined to be shared by the object are activated such that the object shares or is configured to share such slices.

Abstract: System and methods for managing execution of software programs on an array of processing units may involve monitoring an amount of processing input at one or more input buffers buffering processing input for each program, assigning task instances of each program to the array for concurrent processing of the processing input of the programs, adjusting a relative portion of an amount of processing input to be processed by each instance of the one or more assigned task instances of a given program based upon whether, on a prior assignment cycle, more or fewer task instances of the given program had been assigned to the array, and causing connection, in accordance with the assigning, of the processing input from each input buffer to a different unit of the processing units to deliver the processing input to the appropriate program.

Abstract: Systems, apparatuses and methods may provide for technology that associates a key domain of a plurality of key domains with a customer boot image, receives the customer boot image from the customer, and verifies the integrity of the customer boot image that is to be securely installed at memory locations determined from an untrusted privileged entity (e.g., a virtual machine manager).

Abstract: A virtual machine kernel protection method and apparatus are disclosed. The method includes: trapping a system call function initiated by an application program (S301); and pointing the system call function to a shadow kernel based on an offset value between a base address of an original kernel of a virtual machine and a base address of the shadow kernel, and determining a corresponding entry address of the system call function in the shadow kernel based on a shadow SSDT in the shadow kernel (S302), where the shadow kernel is constructed in a nonpaged pool of the original kernel of the virtual machine, and the shadow kernel is executable kernel code constructed based on an image file of the original kernel of the virtual machine.

Abstract: A method, apparatus, and/or computer program product generates a predictive data structure for an application when operating offline in a network connected data processing system, the application comprising source code having an execution path. The method comprises: determining an exit point within the source code of the application; determining, from the exit point, an execution path comprising at least one conditional statement; identifying one or more branches of the at least one identified conditional statement and for each identified branch determining an expected response; for each determined expected response, generating a data structure from the response; continuing along the execution path of the source code from the exit point and replacing each request for a resource in the source code with a pointer to the generated data structure; and executing the source code with the pointer to the generated data structure from the determined exit point.

Abstract: Technical solutions are described for machine-assisted workflow execution, the workflow includes a sequence of workflow steps. An example method includes, pulling a preliminary update for the workflow from a data source and modifying the workflow dynamically. The method further includes selecting a workflow step for execution, and responsively, pulling updated information for the workflow step from the data source. The method further includes retrieving, from the data source, first reasoning information being indicative of whether to update the workflow step. If the first reasoning information is indicative of performing an update, updating the workflow step dynamically using the updated information, and executing the updated workflow step.

Abstract: A system and method for sharing services provides for generating one or more trigger conditions associated with a process executable in a source container having a source namespace in a source pod, executing the process in the source container, and when a trigger condition occurs, interrupting the executed process and moving the process into a target pod by switching from the source namespace of the source container to a target namespace of the target pod. The trigger condition may be associated with a service executable in a target container having the target namespace in the target pod.

Abstract: Technical solutions are described for a machine-assisted workflow execution. An example method includes selecting a workflow for interactive execution, the workflow includes a sequence of workflow steps, and responsively, identifying a preliminary update for the workflow from a data source. The method further includes authenticating the data source, and if the data source is a trusted data source, pulling the preliminary update from the data source and modifying the workflow dynamically. The method further includes selecting a workflow step for execution, and responsively, pulling an updated information for the workflow step from the data source. The method further includes executing the workflow step using the pulled updated information, the execution including changing a target system. The method further includes accumulating execution information and pushing the execution information to the data source upon completion of the workflow step.