Microsoft Technology Licensing, LLC

Siddhartha Sen

Jitendra Dattatraya Padhye

Jacob Rubin Lorch

Andrea D'Amato

Vladimir Petter

Carlos Garcia Jurado Suarez

John C Langford

Richard Lloyd Hughes

Aleksandrs Slivkins

Alekh Agarwal

Joseph M Joy

Nikolai Tillmann

Omar Rogelio Alonso

Margus Veanes

Vasileios Kandylas

Serge-Eric Tremblay

Leon Bottou

Colin L Campbell

Lihong Li

Jake M Hofman

Miroslav Dudik

Amit Date

Markus Cozowicz

Jimmy C Yu

Sarah L Bird

Techniques for employing a decentralized sleep management service are described herein. In some instances, each computing device of a group of computing devices periodically shares information about itself with each other computing device of the group. With this information, each computing device within the group that is awake and capable of managing other devices selects a subset of devices to probe. The devices then probe this subset to determine whether the probed devices are asleep. In response to identifying a sleeping device, the probing device takes over management of the sleeping device. Managing the sleeping device involves informing other devices of the group that the sleeping device is being managed, in addition to monitoring requests for services on the sleeping device. In response to receiving a valid request for a service hosted by the sleeping device, the managing device awakens the sleeping device and ceases managing the now-woken device.

Decentralized sleep management

The claimed subject matter includes techniques for providing an application testing service with a user interface that enables a user to evaluate performance data for computer implemented decision policies. An example method includes displaying a first reward statistic comprising an actual performance result for a policy implemented by an application. The method also includes obtaining experimental data corresponding to previously implemented policies, computing a second reward statistic for a hypothetical policy using a reward function applied to the experimental data. The method also includes displaying the second reward statistic together with the first reward statistic to enable a user to compare the first reward statistic and the second first reward statistic.

Application testing

The claimed subject matter includes techniques for providing an application testing service. An example method includes receiving context information from a client system, the context information comprising parameters that describe details of a user interaction with an application under test (AUT). The method also includes receiving a set of potential actions from the client system. The method also includes identifying a selected action from the set of potential actions and sending the selected action to the client system, wherein the AUT is customized based on the selected action. The method also includes receiving reward data from the client system based on a user's interaction with the AUT. The method also includes storing the context information, the selected action, and the reward data to a log of application test data.

Techniques for designing an awareness engine that organizes and serves popularly discussed and viral online content in response to user search queries. In an aspect, quality online content is identified by analyzing posts by users of a social network over specific time periods. For each item of quality online content identified, a virality score is calculated, and a social signature is constructed. The social signature can be constructed from the content itself, as well as from posts referencing the content. Based on this processing, relevant quality online content having the highest virality scores may be retrieved and served in response to user queries. Further techniques are provided for designing a user interface for the awareness engine.

Awareness engine

Described is a technology by which a relative load of network traffic handling is determined between servers of a cluster, based upon time values that correspond to the time taken by each server to handle a packet. Load may then be transferred between the servers based upon the relative load, for example by having a less-loaded server take some of the responsibility for processing incoming traffic from a more-loaded server. For example, the processing time of a server may be determined by when a receiving server receives a request packet, and when that server sends a return packet. A round trip time for a request and return communication may also be established. A logical tree of nodes representing the servers may be constructed to select pairs of servers for balancing with one another, with the selection algorithm operating recursively, in parallel, and/or repeatedly, until the cluster is balanced.

Dynamic network load balancing using roundtrip heuristic

Aspects of the subject matter described herein relate to client affinity in distributed load balancing systems. In aspects, a request from a requester is sent to each server of a cluster. Each server determines whether it has affinity to the requester. If so, the server responds to the request. Otherwise, if the request would normally be load balanced to the server, the server queries the other servers in the cluster to determine whether any of them have affinity to the requester. If one of them does, the server drops the request and allows the other server to respond to the request; otherwise, the server responds to the request.

Client affinity in distributed load balancing systems

Described is a technology in a network load balancing system (node cluster), by which client affinity is preserved across cluster configuration changes, including for new connections from a previous client. Each node maintains a list of the clients that are to remain (have affinity, or 'stickiness') with that node, including following bucket redistribution resulting from convergence. Each affinity list is communicated during convergence so that other nodes may build an exception list or lists. Via a node's exception list, the node that owns a bucket corresponding to a client knows of the affinity with another node and thus drops any packets from that client. Affinity may expire, whereby the node having affinity with that client releases it and notifies the node owning the bucket for that client that the client is no longer to be treated as an exception.

Maintaining client affinity in network load balancing systems

Techniques for testing software applications in stack-based computing environments are discussed. A tested application is executed at predetermined logical positions in a stack, such as at a layer of the OSI reference model. An expected result of an operation performed by the application is identified. A first set of computer-executable instructions is installed at a first position logically above the tested application, and a second set of computer-executable instructions is installed at a second position logically below the tested application. One or both sets of instructions simulate inputs to the application. The application is executed based on the simulated inputs, and one or both sets of instructions are used to compare outputs from the application with the expected result. Various, virtually unlimited tests can be performed on the software application without the use of extensive test infrastructure.

Software testing techniques for stack-based environments

Diagnosing problems in distributed systems. In one aspect, a model of a distributed system defines trace statements are generated by various nodes of the system and placed in log files. The log files are sent to an automatic validator that attempts to reconcile the trace statements against the model. Results of the attempt are indicated. In another aspect, trace statements are received by a multiplexer that creates an ordering via sequence numbers. The ordering is forwarded to an automatic validator to determine whether the trace statements indicate correct behavior.

Growing community of inventors

New York, NY, United States of America

Siddhartha Sen