Abstract: Methods are disclosed that dynamically improve soft real-time task performance in virtualized computing environments under the management of an enhanced hypervisor comprising a credit scheduler. The enhanced hypervisor analyzes the on-going performance of the domains of interest and of the virtualized data-processing system. Based on the performance metrics disclosed herein, some of the governing parameters of the credit scheduler are adjusted. Adjustments are typically performed cyclically, wherein the performance metrics of an execution cycle are analyzed and, if need be, adjustments are applied in a later execution cycle. In alternative embodiments, some of the analysis and tuning functions are in a separate application that resides outside the hypervisor. The performance metrics disclosed herein include: a “total-time” metric; a “timeslice” metric; a number of “latency” metrics; and a “count” metric.

Abstract: The present disclosure is based on a multi-core or multi-processor virtualized environment that comprises both time-sensitive and non-time-sensitive tasks. The present disclosure describes techniques that use a plurality of criteria to choose a processing resource that is to execute tasks. The present disclosure further describes techniques to re-schedule queued tasks from one processing resource to another processing resource, based on a number of criteria. Through load balancing techniques, the present invention both (i) favors the processing of soft real-time tasks arising from media servers and applications, and (ii) prevents “starvation” of the non-real-time general computing applications that co-exist with the media applications in a virtualized environment. These techniques, in the aggregate, favor the processing of soft real-time tasks while also reserving resources for non-real-time tasks.

Abstract: Systems and methods that enable migration for state of an application, from a primary machine to a backup machine in platform virtualization systems. The migration employs a hybrid approach, wherein both a hypervisor, and an application itself determine states that are to migrate from the primary machine to the backup machine. Based on a direct communication between the application and the hypervisor—without assistance of local operating system—the hypervisor arranges for migration of the required states over to the backup virtual machine.

Abstract: A technique is disclosed that evaluates a network path between (i) a first node in a first subnetwork of endpoint nodes, such as IP phones, and (ii) a second node in a second subnetwork. A “ricochet” node in the network path evaluates the path by probing one or both subnetworks, where the ricochet node acts as relay for traffic packets being transmitted between the two subnetworks. A given relay has only to probe a single, representative node within a subnetwork at any given time in order to obtain performance data that is representative of the subnetwork overall. By probing the representative node, the relay is able to acquire an assessment of network conditions that is valid for the path between the relay and any endpoint in the subnetwork. As a result, the disclosed technique reduces the probing overhead when many endpoint nodes on a given subnetwork are simultaneously active and experiencing adverse network conditions.

Abstract: A system evaluates callers, into a contact center, for possible employment. The evaluations occur while the caller waits in a contact center queue and provide a rating of the callers as potential employees. Ratings may be generated or accumulated from one or more interactions with the contact center, where each interaction with the caller can provide information about the caller's suitability as an employee. Good candidates may be interviewed automatically and/or by a manager. Those candidates that receive good ratings/evaluations and are interested in the position may be hired or provided incentives to help the call center respond to calls.

Abstract: A feature activation system provides a mixed computing environment that includes a server and cloud computing. The hybrid model splits the execution of a communication feature between the cloud and the enterprise server installed at or with the enterprise. Service activation is linked to a portal that can communicate with either an intermediary system or directly with an entity executing computer programs in the cloud. When the customer desires to use a feature, the customer accesses the portal and activates the feature the enterprise desires. In the background, the portal instantiates a virtual machine, on any cloud platform, and then installs the feature with virtual machine on that cloud server. To execute feature, the enterprise server and the virtual machine exchange information between the server and the cloud and allow the feature to access the enterprise server or enterprise data.

Abstract: An apparatus and methods are disclosed for intelligently determining when to merge transactions to backup storage. In particular, in accordance with the illustrative embodiment, queued transactions may be merged based on a variety of criteria, including, but not limited to, one or more of the following: the number of queued transactions; the rate of growth of the number of queued transactions; the calendrical time; estimates of the time required to execute the individual transactions; a measure of importance of the individual transactions; the transaction types of the individual transactions; a measure of importance of one or more data updated by the individual transactions; a measure of availability of one or more resources; a current estimate of the time penalty associated with shadowing a page of memory; and the probability of rollback for the individual transactions, and for the merged transaction.

Abstract: A method is disclosed for adaptively and intelligently partitioning traffic among a plurality of communications channels, without injecting probe traffic into any of the channels. In accordance with the illustrative embodiment, a source node transmits traffic to a receiving node via K communications channels in accordance with partition coefficients ?1, . . . , ?K, and the source node receives information regarding the quality of service (QoS) provided by each of the communications channels. The source node adjusts the values of the partition coefficients ?1, . . . , ?K adaptively based on: the current channel QoS information, prior channel QoS information, the prior values of ?1, . . . , ?K, and a measure of channel independence for one or more pairs of communications channels.

Abstract: An apparatus and method for improving performance in high-availability systems are disclosed. In accordance with the illustrative embodiment, pages of memory of a primary system that are to be shadowed are initially copied to a backup system's memory, as well as to a cache in the primary system. A duplication manager process maintains the cache in an intelligent manner that significantly reduces the overhead required to keep the backup system in sync with the primary system, as well as the cache size needed to achieve a given level of performance. Advantageously, the duplication manager is executed on a different processor core than the application process executing transactions, further improving performance.

Abstract: Methods are disclosed that dynamically improve soft real-time task performance in virtualized computing environments under the management of an enhanced hypervisor comprising a credit scheduler. The enhanced hypervisor analyzes the on-going performance of the domains of interest and of the virtualized data-processing system. Based on the performance metrics disclosed herein, some of the governing parameters of the credit scheduler are adjusted. Adjustments are typically performed cyclically, wherein the performance metrics of an execution cycle are analyzed and, if need be, adjustments are applied in a later execution cycle. In alternative embodiments, some of the analysis and tuning functions are in a separate application that resides outside the hypervisor. The performance metrics disclosed herein include: a “total-time” metric; a “timeslice” metric; a number of “latency” metrics; and a “count” metric.

Abstract: A method for scheduling the execution of tasks on a processor is disclosed. The purpose of the method is in part to serve the special needs of soft real-time tasks, which are time-sensitive. A parameter ? is an estimate of the amount of time required to execute the task. Another parameter ? is the maximum amount of time that the task is to spend in a queue before being executed. In the illustrative embodiment, the preferred wait time ?i for a newly-arrived task Ti is expected to be met though the insertion of the newly-arrived task Ti into a position k in a queue such that position k respects the task's preferred wait time ?i in light of the expected execution times of the other tasks already in the queue.

Abstract: The present disclosure is based on a multi-core or multi-processor virtualized environment that comprises both time-sensitive and non-time-sensitive tasks. The present disclosure describes techniques that use a plurality of criteria to choose a processing resource that is to execute tasks. The present disclosure further describes techniques to re-schedule queued tasks from one processing resource to another processing resource, based on a number of criteria. Through load balancing techniques, the present invention both (i) favors the processing of soft real-time tasks arising from media servers and applications, and (ii) prevents “starvation” of the non-real-time general computing applications that co-exist with the media applications in a virtualized environment. These techniques, in the aggregate, favor the processing of soft real-time tasks while also reserving resources for non-real-time tasks.

Abstract: Methods that enable the detection and handling of lost messages during load-balancing routing protocols are disclosed. In accordance with the illustrative embodiment, when a candidate intermediate node N receives a routing-protocol message, node N performs: (1) a first procedure that is capable of detecting some lost routing-protocol messages that were previously transmitted by node N, and (2) a second procedure that is capable of detecting some lost routing-protocol messages that were previously transmitted by a neighbor of node N.

Abstract: A method for providing priority access to 802.11 endpoints. The method includes the steps of sending a Clear To Send (CTS) frame from a designated station, without requiring a Request to Send (RTS) frame from a first station. The CTS frame includes a field identifying the first station for commencing transmission, and a field indicating a duration of transmission. A deferring step is also performed for deferring any transmissions of stations other than the first station until after the duration indicated in the CTS frame has passed.

Abstract: An apparatus and method are disclosed that enable a first telecommunications endpoint to ensure that a second endpoint is receiving the first endpoint's packet stream transmissions with a satisfactory waveform quality. When the second endpoint receives the packet stream, it decodes the media waveform from the stream, encodes the waveform back into a second packet stream, and transmits some or all of the packets in the second stream back to the first endpoint. The first endpoint then decodes the received waveform in the second stream and compares it to the original waveform transmitted to the second endpoint. Based on the comparison, the first endpoint adjusts the value of a quality indication, and provides the quality indication to its user and to the second endpoint. Advantageously, the user at the second endpoint is able to determine whether the received waveform is, in fact, close enough to the waveform that the first endpoint's user intended to be received and understood.

Abstract: Techniques for performing rapid fault detection and recovery in communication networks are disclosed. For example, in one aspect of the invention, a technique for detecting one or more conditions in a communication network comprises the following steps/operations. One or more keep-alive packets are transmitted from a source node in the communication network to a destination node in the communication network over two or more paths between the source node and the destination node, wherein the two or more paths are at least partially disjoint. Upon receipt of the one or more keep-alive packets at the destination node via the two or more paths, at least one quality measure is computed at the destination node for each of the two or more paths, the at least one quality measure being indicative of one or more conditions in the communication network.

Abstract: A method and apparatus are disclosed that enable a call-processing server to extend a received call out to a telecommunications terminal endpoint, wherein the terminal, such as a hotel room phone, is local to and accessible only through an intermediate point, such as a hotel switchboard. Also disclosed are a method and apparatus that enable a data-processing system, such as a server, to determine whether or not to grant a telecommunications terminal endpoint one or more privileges, without some of the disadvantages of the prior art. The methods and apparatus that are taught in this disclosure can be used for extending the incoming call to the endpoint independently of or in the absence of determining whether or not to grant privileges to the endpoint.

Abstract: A method is disclosed for conducting a search in which measurements of a time-varying property are made and updated during the search, and in which the measurements might be uncertain. In accordance with the illustrative embodiment, one or more search algorithm parameters (e.g., the maximum branching factor of a search tree, a depth cutoff for a search tree, a time cutoff, a threshold, etc.) are adjusted dynamically during the search based on at least one of: the degree of uncertainty of the measurements, the variability of measurements over time (e.g., standard deviation, etc.), and the fraction of members whose measurement is better than a threshold. In addition, the illustrative embodiment enables the search space to be pruned based on these criteria.

Abstract: A method is disclosed for adaptively and intelligently partitioning traffic among a plurality of communications channels, without injecting probe traffic into any of the channels. In accordance with the illustrative embodiment, a source node transmits traffic to a receiving node via K communications channels in accordance with partition coefficients ?1, . . . , ?K, and the source node receives information regarding the quality of service (QoS) provided by each of the communications channels. The source node adjusts the values of the partition coefficients ?1, . . . , ?K adaptively based on: the current channel QoS information, prior channel QoS information, the prior values of ?1, . . . , ?K, and a measure of channel independence for one or more pairs of communications channels.

Abstract: A method and apparatus for determining a location of a transmitter includes taking a Received Signal Strength (RSSI) measurement at a plurality of locations. Next, a known transmit power is subtracted from each of the RSSI measurements to produce a Propagation Loss Vector (PLV) for each location of the plurality of locations. A model is developed from the PLVs, the model including a plurality of grid points. A candidate Transmit Power Vector (TPV) is produced by subtracting the PLV for a candidate location from the RSSI measurement. Each of the RSSI measurements are matched against each TPV of the model. Once all the grid points have been evaluated, the grid point having a best match is selected as a location of the transmitter.