Abstract: Exemplary methods, apparatuses, and systems include a client virtual machine processing a system call for a device driver to instruct a physical device to perform a function and transmitting the system call to an appliance virtual machine to execute the system call. The client virtual machine determines, in response to the system call, that an established connection with the appliance virtual machine has switched from a first protocol to a second protocol, the first and second protocols including a high-performance transmission protocol and Transmission Control Protocol and Internet Protocol (TCP/IP). The client virtual machine transmits the system call to the appliance virtual machine according to the second protocol. For example, the established connection may switch to the second protocol in response to the client virtual machine migrating to the first host device from a second host device.

Abstract: The method may include collecting performance data relating to processing nodes of a computer system which provide services via one or more applications, analyzing the performance data to generate an operational profile characterizing resource usage of the processing nodes, receiving a set of attributes characterizing expected performance goals in which the services are expected to be provided, and generating at least one provisioning policy based on an analysis of the operational profile in conjunction with the set of attributes. The at least one provisioning policy may specify a condition for re-allocating resources associated with at least one processing node in a manner that satisfies the performance goals of the set of attributes. The method may further include re-allocating, during runtime, the resources associated with the at least one processing node when the condition of the at least one provisioning policy is determined as satisfied.

Abstract: A comprehensive approach to streaming backups for virtual machines (“VMs”) in a storage management system comprises improvements to the assignment of data agent proxies for VM secondary copy operations. New considerations in performing a VM streaming backup job include without limitation: determining and enforcing a system-wide per-proxy limit of concurrent data streams; generating an ordered priority list of the VMs to be backed up as a basis for choosing which proxies will back up the respective VM, though the illustrative system may not strictly adhere to the priority list based on further considerations; identifying a next available proxy based on data stream utilization at the proxy; and dynamically re-generating the priority list and re-evaluating considerations if some VMs become “stranded” due to a failure to be backed up. Secondary copy operations are distributed to proxies in ways that improve the chances of successfully completing VM streaming backups.

Abstract: A comprehensive approach to streaming backups for virtual machines (“VMs”) in a storage management system comprises improvements to the assignment of data agent proxies for VM secondary copy operations. New considerations in performing a VM streaming backup job include without limitation: determining and enforcing a system-wide per-proxy limit of concurrent data streams; generating an ordered priority list of the VMs to be backed up as a basis for choosing which proxies will back up the respective VM, though the illustrative system may not strictly adhere to the priority list based on further considerations; identifying a next available proxy based on data stream utilization at the proxy; and dynamically re-generating the priority list and re-evaluating considerations if some VMs become “stranded” due to a failure to be backed up. Secondary copy operations are distributed to proxies in ways that improve the chances of successfully completing VM streaming backups.

Abstract: A computer-implemented method includes identifying a primary computing platform, identifying one or more secondary computing platforms, and identifying a requesting virtual server. The requesting virtual server resides on the primary computing platform and is associated with one or more requesting clients. One or more donating virtual servers are identified. The donating virtual servers reside on the primary computing platform and are associated with one or more donating clients. One or more external virtual servers are identified. The external virtual servers reside on the secondary computing platforms. A resource donation scenario is determined. The resource donation scenario includes one or more resource exchanges between the requesting virtual server and the donating virtual servers. A resource adjustment scenario is determined. The resource adjustment scenario includes one or more resource exchanges between the external virtual servers.

Abstract: Techniques and mechanisms provide a flexible mapping for physical functions and virtual functions in an environment including virtual machines.

Abstract: The present disclosure is directed to enhanced virtual function capabilities in a virtualized network environment. In general, devices may comprise physical and virtualized resources. The physical resources may comprise at least a network adaptor that may handle incoming data from a network and outgoing data to the network. The virtualized resources may comprise at least one virtual machine (VM) and a corresponding interface. The corresponding interface may be one of a physical interface, a virtual interface or a “super” virtual interface. The physical interface may provide a first set of capabilities allowing the VM to access (e.g., control) at least the network adaptor. The virtual interface may provide a second set of capabilities that is a subset of the first set. The super virtual interface may provide a third set of capabilities including the second set of capabilities and at least one additional capability from the first set of capabilities.

Abstract: Load balancing reduces memory consumption in a virtual computing environment. Disk blocks in a cluster of hosts are monitored for redundancy. Execution of virtual machines may be migrated to different hosts within the cluster to balance loading.

Abstract: A method for determining parallel-processing parameters including: randomly generating first sample points each having a coordinate value representing the number of nodes to be used for running a first program and the number of processes per node to be executed in the running of the first program, calculating evaluation values of the respective first sample points based on information collected in the running, calculating a first statistics from the evaluation values; repeating the generating of the first sample points until the first statistic becomes equal to or smaller than a first threshold; and determining, based on a result of interpolation of the evaluation values of the first and the second sample points, the number of nodes and the number of processes that are recommended for running the first program.

Abstract: A system, apparatus, and method for thread synchronization is provided. In one embodiment, a network system receives a signal from a first computing machine, and determines whether one or more processes are waiting for the signal. The network system also transmits the signal to one of the one or more processes on the first computing machine or a second computing machine to execute a thread of the process.

Abstract: A process owner platform may be associated with a cloud embedded big data application and may exchange information with a tenant service executor platform. The process owner platform may establish a process using a process tenant template, the process being associated with public and private data and transmit, to the remote tenant service executor platform, information including the public data (without including the private data). The process owner platform may then receive result data and a process state identifier and establish a virtual process such that it is associated with the public data, the private data, and the result data. The process owner platform may also execute control logic in accordance with the process state identifier to materialize the virtual process into a process or a process tenant template, and the materialized process or process tenant template may associated with the public data, the private data, and the result data.

Abstract: Initial configuration of access for a client device to a streamed application may be initiated in response to receiving a request to enable access. The application may not, in some cases, have been configured for streaming. The application may execute on a virtual computing node assigned to run the application in the context of a user account created to run the application. A link for initiating the application stream may be sent to the client. A capture process detects resources accessed by the application and streams them to the client. Input from the client is inserted into the application's input/output streams by the capture process.

Abstract: The subject technology addresses the need in the art for improving intra-cloud migration of virtual machines in a cloud computing environment. A hash database may be prepopulated with key-value pairs corresponding to hash IDs and associated data chunks of a virtual machine image. In this regard, the virtual machine image may be divided into chunks using boundaries chosen by a Rabin fingerprinting technique. A hash (e.g., MD5 or SHA-1) may be computed over each chunk and act as a unique identifier for the data contained in each chunk. At appropriate times, one or more hash IDs are sent instead of the actual data chunks between clouds when performing the inter-cloud migration of a virtual machine.

Abstract: A method for performance requirement estimation includes: acquiring system performance requirement information indicating requirements of a performance value with respect to processes pertaining to each of processing classifications; acquiring resource information indicating the amount of resources with respect to a plurality of second machines included in a new system to be configured to perform the processes pertaining to each of the processing classifications; determining whether or not the new system satisfies requirements of a performance value with respect to a processes pertaining to each of the processing classifications in accordance with the system performance requirement information, the resource information, and a model configured to output a performance value with respect to the processes pertaining to each of the processing classifications in accordance with an input indicating the amount of resources to be distributed for performing the processes; and outputting a determination result obtained

Abstract: Information representative of a graph-based program specification has a plurality of components, each of which corresponds to a task, and directed links between ports of said components. A program corresponding to said graph-based program specification is executed. A first component includes a first data port, a first control port, and a second control port. Said first data port is configured to receive data to be processed by a first task corresponding to said first component, or configured to provide data that was processed by said first task corresponding to said first component. Executing a program corresponding to said graph-based program specification includes: receiving said first control information at said first control port, in response to receiving said first control information, determining whether or not to invoke said first task, and after receiving said first control information, providing said second control information from said second control port.

Abstract: Optimized placement of virtual machines in a cloud environment is based on factors that include processor-memory affinity. A smart migration mechanism (SMM) predicts an optimization score for multiple permutations of placing virtual machines on a target system to create an optimal move list. The optimization score is a theoretical score calculated using dynamic platform optimization (DPO). The SMM may allow the user to set initial parameters and change the parameters to create potential changes lists. The move lists are ranked to allow the user to select the optimal change list to provide the best affinity, quickest fulfillment of requirements and least disruption for a given set of parameters.

Abstract: Optimized placement of virtual machines in a cloud environment is based on factors that include processor-memory affinity. A smart migration mechanism (SMM) predicts an optimization score for multiple permutations of placing virtual machines on a target system to create an optimal move list. The optimization score is a theoretical score calculated using dynamic platform optimization (DPO). The SMM may allow the user to set initial parameters and change the parameters to create potential changes lists. The move lists are ranked to allow the user to select the optimal change list to provide the best affinity, quickest fulfillment of requirements and least disruption for a given set of parameters.

Abstract: A non-transitory computer-readable storage medium storing a control program that causes a computer to execute a process, the process including obtaining, for each of a plurality of job flows to which coincident input data is inputted, data excluded from the coincident input data of each of the plurality of job flows by a data extraction process or information specifying the excluded data, each of the plurality of job flows defining a plurality of processes including the data extraction process to be executed, and determining whether the plurality of job flows whose output data are coincident each other are aggregated or not based on the excluded data or the information specifying the excluded data.

Abstract: Provided is a system and method for a multi-tenant datacenter with nested hypervisors. This is provided by at least two physical computing systems each having at least one processor and memory store adapted to provide a first level Hypervisors, each providing a First Virtual Computing Environment with a plurality of inactive Virtual Hypervisors nested therein. The multi tenant data center is structured and arranged to activate a Virtual Hypervisor on one of the at least two Hypervisors and automatically migrate the at least one Customer VM from a Customer Hypervisor to the Active Virtual Hypervisor; and evacuate the remaining inactive Virtual Hypervisors from the Hypervisor supporting the Active Hypervisor to another of the at least two Hypervisors supporting inactive Virtual Hypervisors.

Abstract: Provided is a method and system for scheduling computing so as to meet the quality of service (QoS) expected in a system by identifying the operation characteristic of an application in real time and enabling all nodes in the system to dynamically change the schedulers thereof organically between each other. The scheduling method includes: detecting an event of requesting a scheduler change; selecting a scheduler corresponding to the event among schedulers; and changing a scheduler of a node, which schedules use of the control unit, to the selected scheduler, without rebooting the node.