Microsoft Technology Licensing, LLC

Xiaowen Shan

Arun Ayyagari

Timothy Mark Moore

Andrew Kadatch

Aaron Hartwell

James E Walsh

Stuart Raymond Patrick

Ronald Eric Gray

Nicole A Bonilla

Alec C Dun

Joseph K W Chan

Steven F Goddard

Dale Koetke

Michael C Price

A Perry Clarke

Marc R Allen

Stephen J Rauch

The performance of client server interactions is measured by the interacting client. The client-generated performance data is efficiently transmitted to one or more servers by incorporating the performance data regarding one or more previous request/response cycles into a subsequent request. Performance data transmission is made more efficient by transmitting performance data context such as client, server and session details once per connection. Performance data is stored on the client until transmitted or until it has aged beyond a server specified maximum age. Performance data is aggregated on the server in memory resident accumulators. The server may have a set of accumulators for each server its clients communicate with as well as a set for each client. An accumulator value crossing a configurable threshold may trigger an event log entry. The number of performance data events in an event class may be limited to a maximum for a time period.

System and method for client side monitoring of client server communications

The present invention leverages high-frequency interrupts and/or low priority threads to accurately determine which computing resources are available. This provides a computing asset (CPUs and/or software applications) with a means to accurately compensate for resource utilization in order to increase its performance. By utilizing the present invention, the computing asset can optimize its performance in a real-time, self-tuning manner. In one instance of the present invention, high intensity, low priority threads are initiated on available CPUs (logical and/or physical) to effectively replace a CPU's idle time with the low priority thread. This thread generally constitutes a computationally-intensive and/or a memory-intensive thread which permits a highly accurate performance measurement to be obtained for available CPU resources. In another instance of the present invention, high-frequency interrupts are initiated on CPUs to compensate for processes that are shorter than a thread's time quantum, providing a more accurate performance counter.

High performance counter for realistic measurement of computer system load

A method and device are disclosed that enable a user to experience continuity by alleviating blocking of an application by a slow or failure-prone connection. The method includes dissociating the user interface from an application-client managing communications with a server over the dynamic connection. Furthermore, the application-client caches user input for later actions using an asynchronous mechanism to enable the user to work with little interruption. Furthermore, adjustable frame sizes based on the error rate and bandwidth-delay increase throughput. Data retransmission is reduced by maintaining state information for the client and the server so that a disrupted transaction is resumed at or close to the point of disruption and in response to media sense-events. Consequently, establishing, tearing down and adjusting network connections in response to events such as: high error rates, increasing latency, availability of better alternative connections, or loss of a connection do not interrupt the user's experience.

Enhancing application performance in dynamic networks

Growing community of inventors

Kirkland, WA, United States of America

Xiaowen Shan