Elastic applications are internally implemented by combining an adaptive application and an elasticity controller. The controller is usually build by making assumptions on the environment, and as long as these assumptions hold the behavior of the controller is predictable. In reality, situations may arise that invalidate these assumptions. For example, the incoming workload oscillates more frequently and with different intensity than the expectation.
The “validity” of these assumption can be checked on line, and the amount of their degradation monitored. In some cases by acting on the environment we may limit the degradation that results from these situations where design assumptions do not hold completely. For example, we may introduce artificial delays inside user requests, when particular patterns on the input workload are identified.
The goal of this project is to investigate and develop filters to introduce such artificial delays in the elastic systems and limit the degradation of their service level.