Adjustment of end user response times according to user expectations for server applications under load

摘要

A system and method are described herein that prioritize users into waiting queues based on the previously measured end user response time for each user or a user's expectancy for a shorter response time. A user profile may be generated for each user based on the user's expectancy, performance needs, or attributes about the user. The system and method may provide access to a server for each user based on their placement and prioritization in each queue, creating distinct server and/or end user response times for distinct users.

主权项

1. A method for adjusting an end user response time for a user accessing a server under load, the method comprising:
receiving a user request from a user terminal; allocating the user request into a request queue; retrieving a user profile corresponding to the user from a user database; determining a priority level for the user profile, wherein the priority level is based on a performance profile created from end user response times detected at the user terminal and at least a service level agreement between the user and a service provider specifying acceptable end user response times, wherein the performance profile is continuously adjusted based on the detected end user response times until the performance profile is stable, and the detection of end user response times by the user terminal is turned off once the performance profile is stable, wherein the end user response times includes a response time as perceived by the end user, including respective client rendering times and client processing times by the user terminal; assigning the user request to one of at least two waiting queues based on the determined priority level; and transmitting the user request to a business application server in accordance to a determined ratio between the at least two waiting queues.